{"version":1,"pages":[{"id":"-Le0cHhGyhfw2opWpXCm","title":"Introduction","pathname":"/neural-networks-and-deep-learning","siteSpaceId":"sitesp_CQZZK","description":""},{"id":"-Le0cOfI7fAQhUbLvoma","title":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning","siteSpaceId":"sitesp_CQZZK","description":""},{"id":"-Le0cOfJ1khHvrW59HXF","title":"第一周：深度学习引言(Introduction to Deep Learning)","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/chapter1","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"}]},{"id":"-Le0cOfKxQXrLDGbgQy0","title":"1.1 神经网络的监督学习(Supervised Learning with Neural Networks)","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/chapter1/logistic-regression-as-a-neural-network","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第一周：深度学习引言(Introduction to Deep Learning)"}]},{"id":"-Le0cOfLTwkghzIZonsk","title":"1.2 为什么神经网络会流行？(Why is Deep Learning taking off?)","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/chapter1/why-is-deep-learning-taking-off","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第一周：深度学习引言(Introduction to Deep Learning)"}]},{"id":"-Le0cOfMBWPUGi_dE4RG","title":"第二周：神经网络的编程基础(Basics of Neural Network programming)","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-2","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"}]},{"id":"-Le0cOfNqBLBozCNA6jx","title":"2.1 二分类(Binary Classification)","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-2/binary-classification","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第二周：神经网络的编程基础(Basics of Neural Network programming)"}]},{"id":"-Le0cOfOpCgeNskEr4CF","title":"2.2 逻辑回归(Logistic Regression)","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-2/logistic-regression","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第二周：神经网络的编程基础(Basics of Neural Network programming)"}]},{"id":"-Le0cOfPp5E4_YZs7Zng","title":"2.3 逻辑回归的代价函数（Logistic Regression Cost Function）","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-2/logistic-regression-cost-function","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第二周：神经网络的编程基础(Basics of Neural Network programming)"}]},{"id":"-Le0cOfQCfxbTWrkioBp","title":"2.4 逻辑回归的梯度下降（Logistic Regression Gradient Descent）","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-2/computation-graph","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第二周：神经网络的编程基础(Basics of Neural Network programming)"}]},{"id":"-Le0cOfRcSCWnYykedno","title":"2.5 梯度下降的例子(Gradient Descent on m Examples)","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-2/gradient-descent-on-m-examples","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第二周：神经网络的编程基础(Basics of Neural Network programming)"}]},{"id":"-Le0cOfSoVa1183nF--W","title":"2.6 向量化 logistic 回归的梯度输出（Vectorizing Logistic Regression’s Gradient Output）","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-2/vectorizing-logistic-regressions-gradient-output","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第二周：神经网络的编程基础(Basics of Neural Network programming)"}]},{"id":"-Le0cOfTgVSPJKWrn2IW","title":"2.7 （选修）logistic 损失函数的解释（Explanation of logistic regression cost function ）","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-2/explanation-of-logistic-regression-cost-functionoptional","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第二周：神经网络的编程基础(Basics of Neural Network programming)"}]},{"id":"-Le0cOfUd6xucskvZInH","title":"Logistic Regression with a Neural Network mindset 代码","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-2/logistic-regression-with-a-neural-network-mindset-v5","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第二周：神经网络的编程基础(Basics of Neural Network programming)"}]},{"id":"-Le0cOfVXAo076vzjx6b","title":"lr_utils.py","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-2/lrutils-py","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第二周：神经网络的编程基础(Basics of Neural Network programming)"}]},{"id":"-Le0cOfW_rnPRbHDNZVK","title":"第三周：浅层神经网络(Shallow neural networks)","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-3","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"}]},{"id":"-Le0cOfXK_3T2lEyZYba","title":"3.1 神经网络概述（Neural Network Overview）","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-3/neural-networks-overview","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第三周：浅层神经网络(Shallow neural networks)"}]},{"id":"-Le0cOfYedabHPtW7mKf","title":"3.2 神经网络的表示（Neural Network Representation ）","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-3/neural-network-representation","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第三周：浅层神经网络(Shallow neural networks)"}]},{"id":"-Le0cOgLioJ3a99mH0eN","title":"3.3 计算一个神经网络的输出（Computing a Neural Network's output ）","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-3/computing-a-neural-networks-output","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第三周：浅层神经网络(Shallow neural networks)"}]},{"id":"-Le0cOgMjJX4wxH0HAog","title":"3.4 多样本向量化（Vectorizing across multiple examples ）","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-3/vectorizing-across-multiple-examples","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第三周：浅层神经网络(Shallow neural networks)"}]},{"id":"-Le0cOgNyx_6DeOw8bAm","title":"3.5 激活函数（Activation functions）","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-3/activation-functions","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第三周：浅层神经网络(Shallow neural networks)"}]},{"id":"-Le0cOgPYkA1urswlVoF","title":"3.6 为什么需要（ 非线性激活函数？（why need a nonlinear activation function?）","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-3/why-do-you-need-non-linear-activation-functions","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第三周：浅层神经网络(Shallow neural networks)"}]},{"id":"-Le0cOgQPOu9pjGppsk6","title":"3.7 激活函数的导数（Derivatives of activation functions ）","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-3/derivatives-of-activation-functions","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第三周：浅层神经网络(Shallow neural networks)"}]},{"id":"-Le0cOgRjfkrlXJjyH92","title":"3.8 神经网络的梯度下降（Gradient descent for neural networks）","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-3/gradient-descent-for-neural-networks","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第三周：浅层神经网络(Shallow neural networks)"}]},{"id":"-Le0cOgSKWT_V9rb7006","title":"3.9 （选修）直观理解反向传播（Backpropagation intuition ）","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-3/backpropagation-intuition","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第三周：浅层神经网络(Shallow neural networks)"}]},{"id":"-Le0cOgTmvUKYr4CNaWu","title":"3.10 随机初始化（Random+Initialization）","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-3/random-initialization","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第三周：浅层神经网络(Shallow neural networks)"}]},{"id":"-Le0cOgU6L8i0d4UjBoy","title":"Planar data classification with one hidden layer","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-3/planar-data-classification-with-one-hidden-layer-v5","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第三周：浅层神经网络(Shallow neural networks)"}]},{"id":"-Le0cOgV5kWtaSPjHzHU","title":"planar_utils.py","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-3/planarutils-py","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第三周：浅层神经网络(Shallow neural networks)"}]},{"id":"-Le0cOgWSpmuTMKMiMAm","title":"testCases.py","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-3/testcasesv2-py","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第三周：浅层神经网络(Shallow neural networks)"}]},{"id":"-Le0cOgXgaOUiaDjIfgO","title":"第四周：深层神经网络(Deep Neural Networks)","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-4","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"}]},{"id":"-Le0cOgYtGwC9Av6g_6y","title":"4.1 深层神经网络（Deep L-layer neural network）","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-4/deep-l-layer-neural-network","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第四周：深层神经网络(Deep Neural Networks)"}]},{"id":"-Le0cOgZSgQS7VxBs2vl","title":"4.2 前向传播和反向传播（Forward and backward propagation）","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-4/forward-and-backward-propagation","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第四周：深层神经网络(Deep Neural Networks)"}]},{"id":"-Le0cOg_EwC6nVFCNrIR","title":"4.3 深层网络中的前向传播（Forward propagation in a Deep Network ）","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-4/forward-propagation-in-a-deep-network","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第四周：深层神经网络(Deep Neural Networks)"}]},{"id":"-Le0cOgazs4ZLoRh4hF_","title":"4.4 为什么使用深层表示？（Why deep representations?）","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-4/why-deep-representations","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第四周：深层神经网络(Deep Neural Networks)"}]},{"id":"-Le0cOgbBwYxBg9BDqyV","title":"4.5 搭建神经网络块（Building blocks of deep neural networks）","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-4/building-blocks-of-deep-neural-networks","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第四周：深层神经网络(Deep Neural Networks)"}]},{"id":"-Le0cOgcEDn1_Fio1xVr","title":"4.6 参数 VS 超参数（Parameters vs Hyperparameters）","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-4/parameters-vs-hyperparameters","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第四周：深层神经网络(Deep Neural Networks)"}]},{"id":"-Le0cOgdqUL6XAukQ6tJ","title":"Building your Deep Neural Network Step by Step","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-4/building-your-deep-neural-network-step-by-step","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第四周：深层神经网络(Deep Neural Networks)"}]},{"id":"-Le0cOgea7cXhCwx8Fbi","title":"dnn_utils.py","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-4/dnnutils-v2-py","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第四周：深层神经网络(Deep Neural Networks)"}]},{"id":"-Le0cOgfRP2sJqBFkC9k","title":"testCases.py","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-4/testcases","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第四周：深层神经网络(Deep Neural Networks)"}]},{"id":"-Le0cOggL9VuRh-XhQh0","title":"Deep Neural Network Application","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-4/deep-neural-network-application","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第四周：深层神经网络(Deep Neural Networks)"}]},{"id":"-Le0cOgh0-6BzwfGHTph","title":"dnn_app_utils.py","pathname":"/neural-networks-and-deep-learning/neural-networks-and-deep-learning/week-4/dnnapputils-py","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第一门课 神经网络和深度学习(Neural-Networks-and-Deep-Learning)"},{"label":"第四周：深层神经网络(Deep Neural Networks)"}]},{"id":"-Le0cOh_gNYhHnYUshDj","title":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"}]},{"id":"-Le0cOhaKGjWFz0jnYJ1","title":"第一周：深度学习的实用层面(Practical aspects of Deep Learning)","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/practical-aspects-of-deep-learning","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"}]},{"id":"-Le0cOhbGZg0K-QuA5S2","title":"1.1 训练，验证，测试集（Train / Dev / Test sets）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/practical-aspects-of-deep-learning/11-xun-lian-ff0c-yan-zheng-ff0c-ceshi-ji-ff08-train-dev-test-sets","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第一周：深度学习的实用层面(Practical aspects of Deep Learning)"}]},{"id":"-Le0cOhdMBV4a6Bb88Vs","title":"1.2 偏差，方差（Bias /Variance）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/practical-aspects-of-deep-learning/12-pian-cha-ff0c-fang-cha-ff08-bias-variance","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第一周：深度学习的实用层面(Practical aspects of Deep Learning)"}]},{"id":"-Le0cOhehgjd1sT_Wo-o","title":"1.3 机器学习基础（Basic Recipe for Machine Learning）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/practical-aspects-of-deep-learning/13-ji-qi-xue-xi-ji-chu-ff08-basic-recipe-for-machine-learning","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第一周：深度学习的实用层面(Practical aspects of Deep Learning)"}]},{"id":"-Le0cOhfZY_ikVQGnJs3","title":"1.4 正则化（Regularization）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/practical-aspects-of-deep-learning/14-zheng-ze-hua-ff08-regularization","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第一周：深度学习的实用层面(Practical aspects of Deep Learning)"}]},{"id":"-Le0cOhgdATzeVJd9JT6","title":"1.5 为什么正则化有利于预防过拟合呢？（Why regularization reduces overfitting?）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/practical-aspects-of-deep-learning/15-wei-shi-yao-zheng-ze-hua-you-li-yu-yu-fang-guo-ni-he-ni-ff1f-ff08-why-regularization-reduces-over","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第一周：深度学习的实用层面(Practical aspects of Deep Learning)"}]},{"id":"-Le0cOhhAXC4Ve2EXcW_","title":"1.6 dropout 正则化（Dropout Regularization）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/practical-aspects-of-deep-learning/16-dropout-zheng-ze-hua-ff08-dropout-regularization","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第一周：深度学习的实用层面(Practical aspects of Deep Learning)"}]},{"id":"-Le0cOhioHjiURIJhvLu","title":"1.7 理解 dropout（Understanding Dropout）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/practical-aspects-of-deep-learning/17-li-jie-dropout-understanding-dropout","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第一周：深度学习的实用层面(Practical aspects of Deep Learning)"}]},{"id":"-Le0cOhjsnEtZhvcu_6_","title":"1.8 其他正则化方法（Other regularization methods）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/practical-aspects-of-deep-learning/18-qi-ta-zheng-ze-hua-fang-fa-ff08-other-regularization-methods","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第一周：深度学习的实用层面(Practical aspects of Deep Learning)"}]},{"id":"-Le0cOhkupFZdgPMjGoY","title":"1.9 归一化输入（Normalizing inputs）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/practical-aspects-of-deep-learning/19-gui-yi-hua-shu-ru-ff08-normalizing-inputs","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第一周：深度学习的实用层面(Practical aspects of Deep Learning)"}]},{"id":"-Le0cOhmx-MPjaA8HRxJ","title":"1.10 梯度消失/梯度爆炸（Vanishing / Exploding gradients）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/practical-aspects-of-deep-learning/110-ti-du-xiao-5931-ti-du-bao-zha-ff08-vanishing-exploding-gradients","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第一周：深度学习的实用层面(Practical aspects of Deep Learning)"}]},{"id":"-Le0cOhnauRU1t8BGdZV","title":"1.11 神经网络的权重初始化（Weight Initialization for Deep Networks）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/practical-aspects-of-deep-learning/111-shen-jing-wang-luo-de-quan-zhong-chu-shi-hua-ff08-weight-initialization-for-deep-networks","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第一周：深度学习的实用层面(Practical aspects of Deep Learning)"}]},{"id":"-Le0cOhouW7RqoKhiLEo","title":"1.12 梯度的数值逼近（Numerical approximation of gradients）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/practical-aspects-of-deep-learning/112-ti-du-de-shu-zhi-bi-jin-ff08-numerical-approximation-of-gradients","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第一周：深度学习的实用层面(Practical aspects of Deep Learning)"}]},{"id":"-Le0cOhpvGaT1iRax80M","title":"1.13 梯度检验（Gradient checking）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/practical-aspects-of-deep-learning/113-ti-du-jian-yan-ff08-gradient-checking","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第一周：深度学习的实用层面(Practical aspects of Deep Learning)"}]},{"id":"-Le0cOhq2kb1P_BPRzBr","title":"1.14 梯度检验应用的注意事项（Gradient Checking Implementation Notes）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/practical-aspects-of-deep-learning/114-ti-du-jian-yan-ying-yong-de-zhu-yi-shi-xiang-ff08-gradient-checking-implementation-notes","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第一周：深度学习的实用层面(Practical aspects of Deep Learning)"}]},{"id":"-Le0cOhraFNEz3dAlHoN","title":"Initialization","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/practical-aspects-of-deep-learning/dai-ma","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第一周：深度学习的实用层面(Practical aspects of Deep Learning)"}]},{"id":"-Le0cOhsnbYGUtv3te4s","title":"Gradient Checking","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/practical-aspects-of-deep-learning/gradient-checking","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第一周：深度学习的实用层面(Practical aspects of Deep Learning)"}]},{"id":"-Le0cOhtEr-voOm53gLF","title":"Regularization","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/practical-aspects-of-deep-learning/regularization","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第一周：深度学习的实用层面(Practical aspects of Deep Learning)"}]},{"id":"-Le0cOhuXl7glbF6wCpr","title":"reg_utils.py","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/practical-aspects-of-deep-learning/regutils-py","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第一周：深度学习的实用层面(Practical aspects of Deep Learning)"}]},{"id":"-Le0cOhvGpROrUBVJCBV","title":"testCases.py","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/practical-aspects-of-deep-learning/testcasespy","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第一周：深度学习的实用层面(Practical aspects of Deep Learning)"}]},{"id":"-Le0cOhwif-YwZyxHrtD","title":"第二周：优化算法 (Optimization algorithms)","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/optimization-algorithms","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"}]},{"id":"-Le0cOhx0KlymJNYajrE","title":"2.1 Mini-batch 梯度下降（Mini-batch gradient descent）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/optimization-algorithms/21-mini-batch-ti-du-xia-jiang-ff08-mini-batch-gradient-descent","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第二周：优化算法 (Optimization algorithms)"}]},{"id":"-Le0cOhy2NvJP5iF_2m8","title":"2.2 理解 mini-batch 梯度下降法（Understanding mini-batch gradient descent）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/optimization-algorithms/22-li-jie-mini-batch-ti-du-xia-jiang-fa-ff08-understanding-mini-batch-gradient-descent","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第二周：优化算法 (Optimization algorithms)"}]},{"id":"-Le0cOhzsWzbcpAjb0zt","title":"2.3 指数加权平均数（Exponentially weighted averages）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/optimization-algorithms/23-zhi-shu-jia-quan-ping-jun-shu-ff08-exponentially-weighted-averages","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第二周：优化算法 (Optimization algorithms)"}]},{"id":"-Le0cOi-JnOhPXl_ZKhI","title":"2.4 理解指数加权平均数（Understanding exponentially weighted averages ）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/optimization-algorithms/24-li-jie-zhi-shu-jiaquanping-jun-shu-ff08-understandingexponentially-weighted-averages","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第二周：优化算法 (Optimization algorithms)"}]},{"id":"-Le0cOi0ZL0NzhfLvs0c","title":"2.5 指 数 加 权 平 均 的 偏 差 修 正 （ Bias correction in exponentially weighted averages ）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/optimization-algorithms/25-zhi-shu-jia-quan-ping-jun-de-pian-cha-xiu-zheng-bias-correction-in-exponentially-weighted-average","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第二周：优化算法 (Optimization algorithms)"}]},{"id":"-Le0cOi2bz9wXiHocUt3","title":"2.6 动量梯度下降法（Gradient descent with Momentum ）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/optimization-algorithms/26-dong-liang-tidu-xia-jiang-fa-ff08-gradient-descent-with-momentum","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第二周：优化算法 (Optimization algorithms)"}]},{"id":"-Le0cOi3r11ZZ0Dv5yq_","title":"2.7 RMSprop( root mean square prop)","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/optimization-algorithms/27-rmsprop","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第二周：优化算法 (Optimization algorithms)"}]},{"id":"-Le0cOi4j8cDgi83Br07","title":"2.8 Adam 优化算法(Adam optimization algorithm)","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/optimization-algorithms/28-adam-you-hua-suan-6cd528-adam-optimization-algorithm","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第二周：优化算法 (Optimization algorithms)"}]},{"id":"-Le0cOi5f1FDHNrTuLOJ","title":"2.9 学习率衰减(Learning rate decay)","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/optimization-algorithms/29-xue-xi-lv-shuai-51cf28-learning-rate-decay","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第二周：优化算法 (Optimization algorithms)"}]},{"id":"-Le0cOi6MK5L_13ooeZE","title":"2.10 局部最优的问题(The problem of local optima)","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/optimization-algorithms/210-ju-bu-zui-you-de-wen-989828-the-problem-of-local-optima","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第二周：优化算法 (Optimization algorithms)"}]},{"id":"-Le0cOi71RIrbcERVYOp","title":"Optimization","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/optimization-algorithms/optimization-methods","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第二周：优化算法 (Optimization algorithms)"}]},{"id":"-Le0cOi8_lWtLFG-Lf9t","title":"opt_utils.py","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/optimization-algorithms/optutils-py","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第二周：优化算法 (Optimization algorithms)"}]},{"id":"-Le0cOi9QZwf8f7lychW","title":"testCases.py","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/optimization-algorithms/testcasespy","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第二周：优化算法 (Optimization algorithms)"}]},{"id":"-Le0cOiAQJAitNQDbla1","title":"第 三 周 超 参 数 调 试 、 Batch 正 则 化 和 程 序 框 架 （Hyperparameter tuning）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/hyperparameter-tuning","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"}]},{"id":"-Le0cOiBM6PsNyv1MeHW","title":"3.1 调试处理（Tuning process）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/hyperparameter-tuning/31-diao-shi-chu-li-ff08-tuning-process","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第 三 周 超 参 数 调 试 、 Batch 正 则 化 和 程 序 框 架 （Hyperparameter tuning）"}]},{"id":"-Le0cOiCglcJaqtghFA5","title":"3.2 为超参数选择合适的范围（Using an appropriate scale to pick hyperparameters）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/hyperparameter-tuning/32-wei-chao-can-shu-xuan-ze-he-shi-de-fan-wei-ff08-using-an-appropriate-scale-to-pick-hyperparameter","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第 三 周 超 参 数 调 试 、 Batch 正 则 化 和 程 序 框 架 （Hyperparameter tuning）"}]},{"id":"-Le0cOiDnrvKZqYjHUua","title":"3.3 超参数训练的实践： Pandas VS Caviar（Hyperparameters tuning in practice: Pandas vs. Caviar）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/hyperparameter-tuning/33-chao-can-shu-xun-lian-de-shi-jian-ff1a-pandas-vs-caviar-hyperparameterstuning-in-practice-pandas","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第 三 周 超 参 数 调 试 、 Batch 正 则 化 和 程 序 框 架 （Hyperparameter tuning）"}]},{"id":"-Le0cOiEM-s_iSPTWNu4","title":"3.4 归一化网络的激活函数（ Normalizing activations in a network）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/hyperparameter-tuning/34-gui-yi-hua-wang-luo-de-ji-huo-han-shu-ff08-normalizing-activations-in-a-network","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第 三 周 超 参 数 调 试 、 Batch 正 则 化 和 程 序 框 架 （Hyperparameter tuning）"}]},{"id":"-Le0cOiFsbiWXqWGmoWf","title":"3.5 将 Batch Norm 拟合进神经网络（Fitting Batch Norm into a neural network）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/hyperparameter-tuning/35-jiang-batch-norm-ni-he-jin-shen-jing-wang-luo-ff08-fitting-batch-norm-into-a-neural-network","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第 三 周 超 参 数 调 试 、 Batch 正 则 化 和 程 序 框 架 （Hyperparameter tuning）"}]},{"id":"-Le0cOiGNcBGovNytDA7","title":"3.6 Batch Norm 为什么奏效？（Why does Batch Norm work?）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/hyperparameter-tuning/36-batch-norm-wei-shi-yao-zou-xiao-ff1f-ff08-why-does-batch-norm-work","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第 三 周 超 参 数 调 试 、 Batch 正 则 化 和 程 序 框 架 （Hyperparameter tuning）"}]},{"id":"-Le0cOiHOLQuTYB6_6Jt","title":"3.7 测试时的 Batch Norm（Batch Norm at test time）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/hyperparameter-tuning/37-ce-shi-shi-de-batch-norm-batch-norm-at-test-time","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第 三 周 超 参 数 调 试 、 Batch 正 则 化 和 程 序 框 架 （Hyperparameter tuning）"}]},{"id":"-Le0cOiIG2iKJWxB2ODs","title":"3.8 Softmax 回归（Softmax regression）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/hyperparameter-tuning/38-softmax-hui-gui-ff08-softmax-regression","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第 三 周 超 参 数 调 试 、 Batch 正 则 化 和 程 序 框 架 （Hyperparameter tuning）"}]},{"id":"-Le0cOiJlhNl7sfLI0sL","title":"3.9 训练一个 Softmax 分类器（Training a Softmax classifier）","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/hyperparameter-tuning/39-xun-lian-yi-ge-softmax-fen-lei-qi-ff08-training-a-softmax-classifier","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第 三 周 超 参 数 调 试 、 Batch 正 则 化 和 程 序 框 架 （Hyperparameter tuning）"}]},{"id":"-Le0cOiKCeLFvD2EipGi","title":"tensorflow tutorial","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/hyperparameter-tuning/tensorflow-tutorial","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第 三 周 超 参 数 调 试 、 Batch 正 则 化 和 程 序 框 架 （Hyperparameter tuning）"}]},{"id":"-Le0cOiLLCuDbZUVbay-","title":"improv_utils.py","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/hyperparameter-tuning/improvutils-py","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第 三 周 超 参 数 调 试 、 Batch 正 则 化 和 程 序 框 架 （Hyperparameter tuning）"}]},{"id":"-Le0cOiMfH8DOTkcsln_","title":"tf_utils.py","pathname":"/neural-networks-and-deep-learning/di-er-men-ke-gai-shan-shen-ceng-shen-jing-wang-luo-chao-can-shu-tiao-shi-zheng-ze-hua-yi-ji-you-hua/improving-deep-neural-networks/hyperparameter-tuning/tfutils-py","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第二门课 改善深层神经网络：超参数调试、 正 则 化 以 及 优 化 (Improving Deep Neural Networks:Hyperparameter tuning, Regulariza"},{"label":"第二门课 改善深层神经网络：超参数调试、正则化以及优化(Improving Deep Neural Networks:Hyperparameter tuning, Regularization and"},{"label":"第 三 周 超 参 数 调 试 、 Batch 正 则 化 和 程 序 框 架 （Hyperparameter tuning）"}]},{"id":"-Le0cOiPehhauyczXJS5","title":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"}]},{"id":"-Le0cOiQYEtdHwLHYBfh","title":"第一周 机器学习（ML）策略（1）（ML strategy（1））","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects/di-yi-zhou-ml-strategy","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"}]},{"id":"-Le0cOiReX-aVIZcIuCK","title":"1.1 为什么是 ML 策略？（Why ML Strategy?）","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects/di-yi-zhou-ml-strategy/11-wei-shi-yao-shi-ml-ce-lveff1f-ff08-why-ml-strategy","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第一周 机器学习（ML）策略（1）（ML strategy（1））"}]},{"id":"-Le0cOiShCDDQfGReYNW","title":"1.2 正交化（Orthogonalization）","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects/di-yi-zhou-ml-strategy/12-zheng-jiao-hua-ff08-orthogonalization","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第一周 机器学习（ML）策略（1）（ML strategy（1））"}]},{"id":"-Le0cOiT4ACUSnxEbq7N","title":"1.3 单一数字评估指标（Single number evaluation metric）","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects/di-yi-zhou-ml-strategy/13-dan-yi-shu-zi-ping-gu-zhi-biao-ff08-single-number-evaluation-metric","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第一周 机器学习（ML）策略（1）（ML strategy（1））"}]},{"id":"-Le0cOiUyOrkN_uffX8p","title":"1.4 满足和优化指标（Satisficing and optimizing metrics）","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects/di-yi-zhou-ml-strategy/14-man-zu-he-you-hua-zhi-biao-ff08-satisficing-and-optimizing-metrics","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第一周 机器学习（ML）策略（1）（ML strategy（1））"}]},{"id":"-Le0cOiVAYdDdcI-wZHr","title":"1.5 训练/开发/测试集划分（Train/dev/test distributions）","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects/di-yi-zhou-ml-strategy/15-xun-7ec3-kai-53d1-ce-shi-jihua-fen-ff08-train-dev-test-distributions","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第一周 机器学习（ML）策略（1）（ML strategy（1））"}]},{"id":"-Le0cOiWCmx8KeyxkLJA","title":"1.6 开发集和测试集的大小（Size of dev and test sets）","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects/di-yi-zhou-ml-strategy/16-kai-fa-ji-he-ce-shi-ji-de-da-xiao-ff08-size-of-dev-and-test-sets","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第一周 机器学习（ML）策略（1）（ML strategy（1））"}]},{"id":"-Le0cOiX4LDv4XFXynZB","title":"1.7 什么时候该改变开发/测试集和指标？（When to change dev/test sets and metrics）","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects/di-yi-zhou-ml-strategy/17-shi-yao-shi-hou-gai-gai-bian-kai-53d1-ce-shi-ji-he-zhi-biao-ff1f-ff08-when-to-change-dev-test-set","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第一周 机器学习（ML）策略（1）（ML strategy（1））"}]},{"id":"-Le0cOiYKNk2Q8StAPTs","title":"1.8 为什么是人的表现？（ Why human-level performance?）","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects/di-yi-zhou-ml-strategy/18-wei-shi-yao-shi-ren-de-biao-xian-ff1f-ff08-why-human-level-performance","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第一周 机器学习（ML）策略（1）（ML strategy（1））"}]},{"id":"-Le0cOiZxz_ObChsMdn0","title":"1.9 可避免偏差（Avoidable bias）","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects/di-yi-zhou-ml-strategy/19-ke-bi-mian-pian-chaff08-avoidable-bias","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第一周 机器学习（ML）策略（1）（ML strategy（1））"}]},{"id":"-Le0cOi_UX-9jJGzMQZ4","title":"1.10 理解人的表现（Understanding human-level performance）","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects/di-yi-zhou-ml-strategy/110-li-jie-ren-de-biao-xian-ff08-understanding-human-level-performance","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第一周 机器学习（ML）策略（1）（ML strategy（1））"}]},{"id":"-Le0cOiaIHZyT8aXyx5M","title":"1.11 超过人的表现（Surpassing human- level performance）","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects/di-yi-zhou-ml-strategy/111-chao-guo-ren-de-biao-xian-ff08-surpassing-human-level-performance","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第一周 机器学习（ML）策略（1）（ML strategy（1））"}]},{"id":"-Le0cOibWycVllzDkkQf","title":"1.12 改善你的模型的表现（Improving your model performance）","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects/di-yi-zhou-ml-strategy/112-gai-shan-nide-mo-xing-de-biao-xian-ff08-improving-your-model-performance","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第一周 机器学习（ML）策略（1）（ML strategy（1））"}]},{"id":"-Le0cOicWkvGHAAs81xc","title":"第二周：机器学习策略（2）(ML Strategy (2))","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects/ml-strategy","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"}]},{"id":"-Le0cOid70cG6QX3QLoW","title":"2.1 进行误差分析（Carrying out error analysis）","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects/ml-strategy/21-jin-xing-wu-cha-fen-xi-ff08-carrying-out-error-analysis","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第二周：机器学习策略（2）(ML Strategy (2))"}]},{"id":"-Le0cOieZtk0U-z2I2jX","title":"2.2 清楚标注错误的数据（Cleaning up Incorrectly labeled data）","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects/ml-strategy/22-qing-chu-biao-zhu-cuo-wu-de-shu-ju-ff08-cleaning-up-incorrectly-labeled-data","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第二周：机器学习策略（2）(ML Strategy (2))"}]},{"id":"-Le0cOifYIgmzO-fwgIG","title":"2.3 快速搭建你的第一个系统，并进行迭代（Build your first system quickly, then iterate）","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects/ml-strategy/23-kuai-su-da-jian-ni-de-di-yi-ge-xi-tong-ff0c-bing-jin-xing-die-dai-ff08-build-your-first-system-qu","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第二周：机器学习策略（2）(ML Strategy (2))"}]},{"id":"-Le0cOigvQE60Pd7BDpu","title":"2.4 在不同的划分上进行训练并测试（Training and testing on different distributions）","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects/ml-strategy/24-zai-bu-tong-de-huafen-shang-jin-xing-xun-lian-bing-ce-shi-ff08-training-and-testing-on-different","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第二周：机器学习策略（2）(ML Strategy (2))"}]},{"id":"-Le0cOihk0oB3halrS4c","title":"2.5 不匹配数据划分的偏差和方差（Bias and Variance with mismatched data distributions）","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects/ml-strategy/25-bu-pi-pei-shu-ju-huafen-de-pian-cha-he-fang-cha-ff08-bias-and-variance-with-mismatched-data-distr","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第二周：机器学习策略（2）(ML Strategy (2))"}]},{"id":"-Le0cOiiQ-kDDw2OibGd","title":"2.6 定位数据不匹配（Addressing data mismatch）","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects/ml-strategy/26-ding-wei-shu-ju-bu-pi-pei-ff08-addressing-data-mismatch","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第二周：机器学习策略（2）(ML Strategy (2))"}]},{"id":"-Le0cOijDNciCOx59-ac","title":"2.7 迁移学习（Transfer learning）","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects/ml-strategy/27-qian-yi-xue-xi-ff08-transfer-learning","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第二周：机器学习策略（2）(ML Strategy (2))"}]},{"id":"-Le0cOikUaG0aIy9jOsS","title":"2.8 多任务学习（Multi-task learning）","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects/ml-strategy/28-duo-ren-wu-xue-xi-ff08-multi-task-learning","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第二周：机器学习策略（2）(ML Strategy (2))"}]},{"id":"-Le0cOilN-NNzWDs_v3D","title":"2.9 什么是端到端的深度学习？（What is end-to-end deep learning?）","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects/ml-strategy/29-shi-yao-shi-duan-dao-duan-de-shen-du-xue-xiff1f-ff08-what-is-end-to-end-deep-learning","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第二周：机器学习策略（2）(ML Strategy (2))"}]},{"id":"-Le0cOimddvVtEWkR7jP","title":"2.10 是否要使用端到端的深度学习？（Whether to use end-to-end learning?）","pathname":"/neural-networks-and-deep-learning/di-san-men-ke-jie-gou-hua-ji-qi-xue-xi-xiang-mu-structuring-machine-learning-projects/di-san-men-ke-structuring-machine-learning-projects/ml-strategy/210-shi-fou-yao-shi-yong-duan-dao-duan-de-shen-du-xue-xi-ff1f-ff08-whether-to-use-end-to-end-learnin","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第三门课 结构化机器学习项目（Structuring Machine Learning Projects）"},{"label":"第二周：机器学习策略（2）(ML Strategy (2))"}]},{"id":"-Le0cOipfu_d9w6Pn1o1","title":"第四门课 卷积神经网络（Convolutional Neural Networks）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"}]},{"id":"-Le0cOiqnbM31RTEQg-W","title":"第一周 卷积神经网络（Foundations of Convolutional Neural Networks）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/foundations-of-convolutional-neural-networks","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"}]},{"id":"-Le0cOircDniqk6j1bPF","title":"1.1 计算机视觉（Computer vision）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/foundations-of-convolutional-neural-networks/11-ji-suan-ji-shi-jue-ff08-computer-vision","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第一周 卷积神经网络（Foundations of Convolutional Neural Networks）"}]},{"id":"-Le0cOis-GUHrB2hQwKt","title":"1.2 边缘检测示例（Edge detection example）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/foundations-of-convolutional-neural-networks/12-bian-yuan-jian-ce-shi-li-ff08-edge-detection-example","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第一周 卷积神经网络（Foundations of Convolutional Neural Networks）"}]},{"id":"-Le0cOitcsJzTCgI6XAA","title":"1.3 更多边缘检测内容（More edge detection）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/foundations-of-convolutional-neural-networks/13-geng-duo-bian-yuan-jian-ce-nei-rong-ff08-more-edge-detection","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第一周 卷积神经网络（Foundations of Convolutional Neural Networks）"}]},{"id":"-Le0cOiu2pS06tqR1SWb","title":"1.4 Padding","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/foundations-of-convolutional-neural-networks/14-padding","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第一周 卷积神经网络（Foundations of Convolutional Neural Networks）"}]},{"id":"-Le0cOiv-PmHZKSn8Rcw","title":"1.5 卷积步长（Strided convolutions）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/foundations-of-convolutional-neural-networks/15-juan-ji-bu-chang-ff08-strided-convolutions","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第一周 卷积神经网络（Foundations of Convolutional Neural Networks）"}]},{"id":"-Le0cOiwFJX00_CEj7cN","title":"1.6 三维卷积（Convolutions over volumes）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/foundations-of-convolutional-neural-networks/16-san-wei-juan-ji-ff08-convolutions-over-volumes","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第一周 卷积神经网络（Foundations of Convolutional Neural Networks）"}]},{"id":"-Le0cOixvhGL3sSMvcq7","title":"1.7 单层卷积网络（One layer of a convolutional network）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/foundations-of-convolutional-neural-networks/17-dan-ceng-juan-ji-wang-luo-ff08-one-layer-of-a-convolutional-network","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第一周 卷积神经网络（Foundations of Convolutional Neural Networks）"}]},{"id":"-Le0cOiygsbEN9NESIj5","title":"1.8 简单卷积网络示例（A simple convolution network example）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/foundations-of-convolutional-neural-networks/18-jian-dan-juan-ji-wang-luo-shi-li-ff08-a-simple-convolution-network-example","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第一周 卷积神经网络（Foundations of Convolutional Neural Networks）"}]},{"id":"-Le0cOizYoMafecd94fm","title":"1.9 池化层（Pooling layers）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/foundations-of-convolutional-neural-networks/19-chi-hua-ceng-ff08-pooling-layers","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第一周 卷积神经网络（Foundations of Convolutional Neural Networks）"}]},{"id":"-Le0cOj-2fA29YxUj_7R","title":"1.10 卷积神经网络示例（Convolutional neural network example）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/foundations-of-convolutional-neural-networks/110-juan-ji-shenjing-wang-luo-shi-li-ff08-convolutional-neural-network-example","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第一周 卷积神经网络（Foundations of Convolutional Neural Networks）"}]},{"id":"-Le0cOj0irWgohFQyaQJ","title":"1.11 为什么使用卷积？（Why convolutions?）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/foundations-of-convolutional-neural-networks/111-wei-shi-yao-shi-yong-juan-ji-ff1f-ff08-why-convolutions","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第一周 卷积神经网络（Foundations of Convolutional Neural Networks）"}]},{"id":"-Le0cOj1vh9kt9Sm1EEq","title":"Convolution model Step by Step","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/foundations-of-convolutional-neural-networks/convolution-model-step-by-step","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第一周 卷积神经网络（Foundations of Convolutional Neural Networks）"}]},{"id":"-Le0cOj20904SFEg1MZU","title":"Convolutional Neural Networks: Application","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/foundations-of-convolutional-neural-networks/convolutional-neural-networks-application","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第一周 卷积神经网络（Foundations of Convolutional Neural Networks）"}]},{"id":"-Le0cOj3WEhsOtyw7-vy","title":"cnn_utils","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/foundations-of-convolutional-neural-networks/cnnutils","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第一周 卷积神经网络（Foundations of Convolutional Neural Networks）"}]},{"id":"-Le0cOj4vUqDG01blggj","title":"第二周 深度卷积网络：实例探究（Deep convolutional models: case studies）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/deep-convolutional-models-case-studies","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"}]},{"id":"-Le0cOj519qcjLkIXXDv","title":"2.1 经典网络（Classic networks）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/deep-convolutional-models-case-studies/22-jing-dian-wang-luoff08-classic-networks","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第二周 深度卷积网络：实例探究（Deep convolutional models: case studies）"}]},{"id":"-Le0cOj6PD8BY5_qBikx","title":"2.2 残差网络（Residual Networks (ResNets)）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/deep-convolutional-models-case-studies/23-can-cha-wang-luo-ff08-residual-networks-resnets","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第二周 深度卷积网络：实例探究（Deep convolutional models: case studies）"}]},{"id":"-Le0cOj7q2LSCrBHeQXc","title":"2.3 残差网络为什么有用？（Why ResNets work?）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/deep-convolutional-models-case-studies/24-can-cha-wang-luo-wei-shi-yao-you-yong-ff1f-ff08-why-resnets-work","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第二周 深度卷积网络：实例探究（Deep convolutional models: case studies）"}]},{"id":"-Le0cOj8UD0JytCBn-q_","title":"2.4 网络中的网络以及 1×1 卷积（Network in Network and 1×1 convolutions）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/deep-convolutional-models-case-studies/25-wang-luo-zhong-de-wang-luo-yi-ji-1-1-juan-ji-ff08-network-in-network-and-1-1-convolutions","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第二周 深度卷积网络：实例探究（Deep convolutional models: case studies）"}]},{"id":"-Le0cOj9l6MJUYX1Y0Ss","title":"2.5 谷歌 Inception 网络简介（Inception network motivation）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/deep-convolutional-models-case-studies/26-gu-ge-inception-wang-luo-jianjie-ff08-inception-network-motivation","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第二周 深度卷积网络：实例探究（Deep convolutional models: case studies）"}]},{"id":"-Le0cOjA8DVaQ65hzBbz","title":"2.6 Inception 网络（Inception network）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/deep-convolutional-models-case-studies/27-inception-wang-luo-ff08-inception-network","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第二周 深度卷积网络：实例探究（Deep convolutional models: case studies）"}]},{"id":"-Le0cOjBJkRl6Um-02JI","title":"2.7 迁移学习（Transfer Learning）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/deep-convolutional-models-case-studies/29-qian-yi-xue-xi-ff08-transfer-learning","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第二周 深度卷积网络：实例探究（Deep convolutional models: case studies）"}]},{"id":"-Le0cOjCssHb4eCNYBoa","title":"2.8 数据扩充（Data augmentation）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/deep-convolutional-models-case-studies/210-shu-ju-kuo-chong-ff08-data-augmentation","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第二周 深度卷积网络：实例探究（Deep convolutional models: case studies）"}]},{"id":"-Le0cOjDkhNYXL3fxXQJ","title":"2.9 计算机视觉现状（The state of computer vision）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/deep-convolutional-models-case-studies/211-ji-suan-ji-shi-jue-xian-zhuang-ff08-the-state-of-computer-vision","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第二周 深度卷积网络：实例探究（Deep convolutional models: case studies）"}]},{"id":"-Le0cOjEmPwIH0mlldEr","title":"Residual Networks","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/deep-convolutional-models-case-studies/residual-networks","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第二周 深度卷积网络：实例探究（Deep convolutional models: case studies）"}]},{"id":"-Le0cOjF18oduQJ7l1iU","title":"Keras tutorial - the Happy House","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/deep-convolutional-models-case-studies/keras-tutorial-happy-house-v2","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第二周 深度卷积网络：实例探究（Deep convolutional models: case studies）"}]},{"id":"-Le0cOjGN8iTnEnD1vYY","title":"kt_utils.py","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/deep-convolutional-models-case-studies/ktutils-py","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第二周 深度卷积网络：实例探究（Deep convolutional models: case studies）"}]},{"id":"-Le0cOjHnKqvN7H9gPYa","title":"第三周 目标检测（Object detection）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/object-detection","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"}]},{"id":"-Le0cOjI22RzRqxJCPUO","title":"3.1 目标定位（Object localization）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/object-detection/31-mu-biao-ding-wei-ff08-object-localization","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第三周 目标检测（Object detection）"}]},{"id":"-Le0cOjJlCrBO91b3tkN","title":"3.2 特征点检测（Landmark detection）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/object-detection/32-te-zheng-dian-jian-ce-ff08-landmark-detection","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第三周 目标检测（Object detection）"}]},{"id":"-Le0cOjKl8jtTeTAEbLc","title":"3.3 目标检测（Object detection）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/object-detection/33-mu-biao-jian-ce-ff08-object-detection","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第三周 目标检测（Object detection）"}]},{"id":"-Le0cOjLrt3IaiJ5WSHX","title":"3.4 卷积的滑动窗口实现（Convolutional implementation of sliding windows）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/object-detection/34-juan-ji-de-hua-dong-chuang-kou-shi-xian-ff08-convolutional-implementation-of-sliding-windows","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第三周 目标检测（Object detection）"}]},{"id":"-Le0cOjMt2BZ7cmS_J5q","title":"3.5 Bounding Box预测（Bounding box predictions）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/object-detection/35-bounding-boxyu-ce-ff08-bounding-box-predictions","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第三周 目标检测（Object detection）"}]},{"id":"-Le0cOjNfTc6EjmtXofJ","title":"3.6 交并比（Intersection over union）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/object-detection/36-jiao-bing-bi-ff08-intersection-over-union","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第三周 目标检测（Object detection）"}]},{"id":"-Le0cOjO2XWdGdWRMFSP","title":"3.7 非极大值抑制（Non-max suppression）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/object-detection/37-fei-ji-da-zhi-yi-zhi-ff08-non-max-suppression","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第三周 目标检测（Object detection）"}]},{"id":"-Le0cOjP13ykDSiqULSf","title":"3.8 Anchor Boxes","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/object-detection/38-anchor-boxes","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第三周 目标检测（Object detection）"}]},{"id":"-Le0cOjQITzbnw5gk9cC","title":"3.9 YOLO 算法（Putting it together: YOLO algorithm）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/object-detection/39-yolo-suan-fa-ff08-putting-it-together-yolo-algorithm","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第三周 目标检测（Object detection）"}]},{"id":"-Le0cOjRXPQf99wyxz8R","title":"3.10 候选区域（选修）（Region proposals (Optional)）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/object-detection/310-hou-xuan-qu-yu-ff08-xuan-xiu-ff09-ff08-region-proposals-optional","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第三周 目标检测（Object detection）"}]},{"id":"-Le0cOjS9QZkOJ2gV6Jc","title":"Autonomous driving application - Car detection","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/object-detection/autonomous-driving-application-car-detection-v3","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第三周 目标检测（Object detection）"}]},{"id":"-Le0cOjTJFSH6tG1XRXv","title":"yolo_utils.py","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/object-detection/yoloutils-py","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第三周 目标检测（Object detection）"}]},{"id":"-Le0cOjULW1oIuUuR98u","title":"第四周 特殊应用：人脸识别和神经风格转换（Special applications: Face recognition &Neural style transfer）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/special-applications","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"}]},{"id":"-Le0cOjVWuFAW0Ia1XmC","title":"4.1 什么是人脸识别？（What is face recognition?）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/special-applications/41-shi-yao-shi-ren-lian-shi-bie-ff1f-ff08-what-is-face-recognition","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四周 特殊应用：人脸识别和神经风格转换（Special applications: Face recognition &Neural style transfer）"}]},{"id":"-Le0cOjWNU6KnHEfjW39","title":"4.2 One-Shot学习（One-shot learning）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/special-applications/42-one-shotxue-xi-ff08-one-shot-learning","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四周 特殊应用：人脸识别和神经风格转换（Special applications: Face recognition &Neural style transfer）"}]},{"id":"-Le0cOjXwFv7eiDqeZ0k","title":"4.3 Siamese 网络（Siamese network）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/special-applications/43-siamese-wang-luo-ff08-siamese-network","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四周 特殊应用：人脸识别和神经风格转换（Special applications: Face recognition &Neural style transfer）"}]},{"id":"-Le0cOjY9QIHHH5PXmEr","title":"4.4 Triplet 损失（Triplet 损失）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/special-applications/44-triplet-sun-shi-ff08-triplet-sun-shi-ff09","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四周 特殊应用：人脸识别和神经风格转换（Special applications: Face recognition &Neural style transfer）"}]},{"id":"-Le0cOjZLUowpUxbZrWg","title":"4.5 面部验证与二分类（Face verification and binary classification）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/special-applications/45-mian-bu-yan-zheng-yu-er-fen-lei-ff08-face-verification-and-binary-classification","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四周 特殊应用：人脸识别和神经风格转换（Special applications: Face recognition &Neural style transfer）"}]},{"id":"-Le0cOj_DRUHEAOlR-N4","title":"4.6 什么是深度卷积网络？（What are deep ConvNets learning?）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/special-applications/47-shi-yao-shi-shen-du-juan-ji-wang-luo-ff1f-ff08-what-are-deep-convnets-learning","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四周 特殊应用：人脸识别和神经风格转换（Special applications: Face recognition &Neural style transfer）"}]},{"id":"-Le0cOjahUTIugk8jYGM","title":"4.7 代价函数（Cost function）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/special-applications/48-dai-jia-han-shu-ff08-cost-function","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四周 特殊应用：人脸识别和神经风格转换（Special applications: Face recognition &Neural style transfer）"}]},{"id":"-Le0cOjb5h3pQ6DsM8BS","title":"4.8 内容代价函数（Content cost function）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/special-applications/49-nei-rong-dai-jia-han-shu-ff08-content-cost-function","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四周 特殊应用：人脸识别和神经风格转换（Special applications: Face recognition &Neural style transfer）"}]},{"id":"-Le0cOjcyOAtmTyKqaWT","title":"4.9 风格代价函数（Style cost function）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/special-applications/410-feng-ge-dai-jia-han-shu-ff08-style-cost-function","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四周 特殊应用：人脸识别和神经风格转换（Special applications: Face recognition &Neural style transfer）"}]},{"id":"-Le0cOjduPrPBxOwj_tG","title":"4.10 一维到三维推广（1D and 3D generalizations of models）","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/special-applications/411-yi-wei-dao-san-wei-tui-guang-ff08-1d-and3d-generalizations-of-models","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四周 特殊应用：人脸识别和神经风格转换（Special applications: Face recognition &Neural style transfer）"}]},{"id":"-Le0cOje054nS_9OVNqy","title":"Art Generation with Neural Style Transfer","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/special-applications/art-generation-with-neural-style-transfer-v2","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四周 特殊应用：人脸识别和神经风格转换（Special applications: Face recognition &Neural style transfer）"}]},{"id":"-Le0cOjfkm-wUpyibS3U","title":"nst_utils.py","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/special-applications/nstutils-py","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四周 特殊应用：人脸识别和神经风格转换（Special applications: Face recognition &Neural style transfer）"}]},{"id":"-Le0cOjgXbKpsA3sR3FA","title":"Face Recognition for the Happy House","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/special-applications/face+recognition+for+the+happy+house+-+v3","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四周 特殊应用：人脸识别和神经风格转换（Special applications: Face recognition &Neural style transfer）"}]},{"id":"-Le0cOjhpqoi3_UHNh2l","title":"fr_utils.py","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/special-applications/frutils-py","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四周 特殊应用：人脸识别和神经风格转换（Special applications: Face recognition &Neural style transfer）"}]},{"id":"-Le0cOjir8Iy-POAFSo_","title":"inception_blocks.py","pathname":"/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/special-applications/inceptionblocks-py","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四门课 卷积神经网络（Convolutional Neural Networks）"},{"label":"第四周 特殊应用：人脸识别和神经风格转换（Special applications: Face recognition &Neural style transfer）"}]},{"id":"-Le0cOkLHbXi4Y2UfxBp","title":"第五门课 序列模型(Sequence Models)","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"}]},{"id":"-Le0cOkM19pDDeI8iYK4","title":"第一周 循环序列模型（Recurrent Neural Networks）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/recurrent-neural-networks","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"}]},{"id":"-Le0cOkN-H8W0tzFl1Tn","title":"1.1 为什么选择序列模型？（Why Sequence Models?）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/recurrent-neural-networks/11-wei-shi-yao-xuan-ze-xu-lie-mo-xing-ff1f-ff08-why-sequence-models","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第一周 循环序列模型（Recurrent Neural Networks）"}]},{"id":"-Le0cOkOxuiXitwTtNPO","title":"1.2 数学符号（Notation）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/recurrent-neural-networks/12-shu-xue-fu-hao-ff08-notation","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第一周 循环序列模型（Recurrent Neural Networks）"}]},{"id":"-Le0cOkPVfB5TlLzEYVI","title":"1.3 循环神经网络模型（Recurrent Neural Network Model）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/recurrent-neural-networks/13-xun-huan-shen-jing-wang-luo-mo-xing-ff08-recurrent-neural-network-model","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第一周 循环序列模型（Recurrent Neural Networks）"}]},{"id":"-Le0cOkQdJkCJb7nV73P","title":"1.4 通过时间的反向传播（Backpropagation through time）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/recurrent-neural-networks/14-tong-guo-shi-jian-de-fan-xiang-chuan-bo-ff08-backpropagation-through-time","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第一周 循环序列模型（Recurrent Neural Networks）"}]},{"id":"-Le0cOkRDG3_n1d9QUR_","title":"1.5 不同类型的循环神经网络（Different types of RNNs）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/recurrent-neural-networks/15-bu-tong-lei-xing-dexun-huan-shen-jing-wang-luo-ff08-different-types-of-rnns","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第一周 循环序列模型（Recurrent Neural Networks）"}]},{"id":"-Le0cOkSmtH4VPnG_agf","title":"1.6 语言模型和序列生成（Language model and sequence generation）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/recurrent-neural-networks/16-yu-yan-mo-xinghe-xu-liesheng-cheng-ff08-language-model-and-sequence-generation","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第一周 循环序列模型（Recurrent Neural Networks）"}]},{"id":"-Le0cOkTK3PTY7402U4F","title":"1.7 对新序列采样（Sampling novel sequences）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/recurrent-neural-networks/17-dui-xin-xu-lie-cai-yang-ff08-sampling-novel-sequences","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第一周 循环序列模型（Recurrent Neural Networks）"}]},{"id":"-Le0cOkU-_AoX-v8ojvZ","title":"1.8 循环神经网络的梯度消失（Vanishing gradients with RNNs）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/recurrent-neural-networks/18-xun-huan-shen-jing-wangluo-de-ti-du-xiao-shi-ff08-vanishing-gradients-with-rnns","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第一周 循环序列模型（Recurrent Neural Networks）"}]},{"id":"-Le0cOkV1SmRrT6Uol_-","title":"1.9 GRU单元（Gated Recurrent Unit（GRU））","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/recurrent-neural-networks/19-grudan-yuan-ff08-gated-recurrent-unit-gru","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第一周 循环序列模型（Recurrent Neural Networks）"}]},{"id":"-Le0cOkW1hsjaP5jF6p3","title":"1.10 长短期记忆（LSTM（long short term memory）unit）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/recurrent-neural-networks/110-chang-duan-qi-ji-yi-ff08-lstm-long-short-term-memory-unit","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第一周 循环序列模型（Recurrent Neural Networks）"}]},{"id":"-Le0cOkXcG73QaLCPr6D","title":"1.11 双向循环神经网络（Bidirectional RNN）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/recurrent-neural-networks/111-shuang-xiang-xun-huan-shenjing-wang-luo-ff08-bidirectional-rnn","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第一周 循环序列模型（Recurrent Neural Networks）"}]},{"id":"-Le0cOkYfhyHPNUzSi24","title":"1.12 深层循环神经网络（Deep RNNs）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/recurrent-neural-networks/112-shen-ceng-xun-huan-shen-jing-wang-luo-ff08-deep-rnns","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第一周 循环序列模型（Recurrent Neural Networks）"}]},{"id":"-Le0cOkZfz7vBvUY0WKi","title":"Building your Recurrent Neural Network","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/recurrent-neural-networks/building+a+recurrent+neural+network+-+step+by+step+-+v3","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第一周 循环序列模型（Recurrent Neural Networks）"}]},{"id":"-Le0cOk_pehmv169ACc4","title":"rnn_utils.py","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/recurrent-neural-networks/rnnutils-py","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第一周 循环序列模型（Recurrent Neural Networks）"}]},{"id":"-Le0cOkaUQ7JkE0I3mjs","title":"Dinosaurus Island -- Character level language model final","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/recurrent-neural-networks/dinosaurus+island+-+character+level+language+model+final+-+v3","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第一周 循环序列模型（Recurrent Neural Networks）"}]},{"id":"-Le0cOkbiucq8T3LY6t7","title":"utils.py","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/recurrent-neural-networks/utilspy","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第一周 循环序列模型（Recurrent Neural Networks）"}]},{"id":"-Le0cOkc20u9A9w3CHey","title":"shakespeare_utils.py","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/recurrent-neural-networks/shakespeareutils-py","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第一周 循环序列模型（Recurrent Neural Networks）"}]},{"id":"-Le0cOkdJWxmwd2Hg4ot","title":"Improvise a Jazz Solo with an LSTM Network","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/recurrent-neural-networks/improvise+a+jazz+solo+with+an+lstm+network+-+v3","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第一周 循环序列模型（Recurrent Neural Networks）"}]},{"id":"-Le0cOkeRHCK6_CaNICp","title":"第二周 自然语言处理与词嵌入（Natural Language Processing and Word Embeddings）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/natural-language-processing-and-word-embeddings","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"}]},{"id":"-Le0cOkf1f993zWKV676","title":"2.1 词汇表征（Word Representation）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/natural-language-processing-and-word-embeddings/21-ci-hui-biao-zheng-ff08-word-representation","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第二周 自然语言处理与词嵌入（Natural Language Processing and Word Embeddings）"}]},{"id":"-Le0cOkgeM63dASlEbP2","title":"2.2 使用词嵌入（Using Word Embeddings）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/natural-language-processing-and-word-embeddings/22-shi-yong-ci-qian-ru-ff08-using-word-embeddings","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第二周 自然语言处理与词嵌入（Natural Language Processing and Word Embeddings）"}]},{"id":"-Le0cOkhG7LDdZ_-ykYQ","title":"2.3 词嵌入的特性（Properties of Word Embeddings）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/natural-language-processing-and-word-embeddings/23-ci-qian-ru-de-texing-ff08-propertiesof-word-embeddings","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第二周 自然语言处理与词嵌入（Natural Language Processing and Word Embeddings）"}]},{"id":"-Le0cOkiSAYh0UUZFTFY","title":"2.4 嵌入矩阵（Embedding Matrix）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/natural-language-processing-and-word-embeddings/24-qian-ru-ju-zhen-ff08-embedding-matrix","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第二周 自然语言处理与词嵌入（Natural Language Processing and Word Embeddings）"}]},{"id":"-Le0cOkj_mnwMUiJjIM_","title":"2.5 学习词嵌入（Learning Word Embeddings）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/natural-language-processing-and-word-embeddings/25-xue-xi-ci-qian-ru-ff08-learning-word-embeddings","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第二周 自然语言处理与词嵌入（Natural Language Processing and Word Embeddings）"}]},{"id":"-Le0cOkkfxcIA7FZlsKG","title":"2.6 Word2Vec","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/natural-language-processing-and-word-embeddings/26-word2vec","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第二周 自然语言处理与词嵌入（Natural Language Processing and Word Embeddings）"}]},{"id":"-Le0cOkl2Wx4s1IKXk_G","title":"2.7 负采样（Negative Sampling）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/natural-language-processing-and-word-embeddings/27-fu-cai-yang-ff08-negative-sampling","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第二周 自然语言处理与词嵌入（Natural Language Processing and Word Embeddings）"}]},{"id":"-Le0cOkmKdOTg0-nIMQC","title":"2.8 GloVe 词向量（GloVe Word Vectors）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/natural-language-processing-and-word-embeddings/28-glove-ci-xiang-liang-ff08-glove-word-vectors","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第二周 自然语言处理与词嵌入（Natural Language Processing and Word Embeddings）"}]},{"id":"-Le0cOknyrXVp2huJ_AG","title":"2.9 情感分类（Sentiment Classification）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/natural-language-processing-and-word-embeddings/29-qing-ganfen-lei-ff08-sentiment-classification","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第二周 自然语言处理与词嵌入（Natural Language Processing and Word Embeddings）"}]},{"id":"-Le0cOko9GJTOPKtz59f","title":"2.10 词嵌入除偏（Debiasing Word Embeddings）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/natural-language-processing-and-word-embeddings/210-ci-qian-ru-chu-pian-ff08-debiasing-word-embeddings","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第二周 自然语言处理与词嵌入（Natural Language Processing and Word Embeddings）"}]},{"id":"-Le0cOkpgawoi4jbh1pY","title":"Operations on word vectors","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/natural-language-processing-and-word-embeddings/operations+on+word+vectors+-+v2","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第二周 自然语言处理与词嵌入（Natural Language Processing and Word Embeddings）"}]},{"id":"-Le0cOkqIkDxUJqvddz1","title":"w2v_utils.py","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/natural-language-processing-and-word-embeddings/w2vutils-py","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第二周 自然语言处理与词嵌入（Natural Language Processing and Word Embeddings）"}]},{"id":"-Le0cOkrFmsTUK9IEX3C","title":"Emojify","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/natural-language-processing-and-word-embeddings/emojify-v2","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第二周 自然语言处理与词嵌入（Natural Language Processing and Word Embeddings）"}]},{"id":"-Le0cOkseIIiDcJ1-MVq","title":"emo_utils.py","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/natural-language-processing-and-word-embeddings/emoutils-py","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第二周 自然语言处理与词嵌入（Natural Language Processing and Word Embeddings）"}]},{"id":"-Le0cOktMQ2IAYyIYYan","title":"第三周 序列模型和注意力机制（Sequence models & Attention mechanism）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"}]},{"id":"-Le0cOkudIyZ-nAJ1hZy","title":"3.1 基础模型（Basic Models）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/31-ji-chu-mo-xing-ff08-basic-models","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第三周 序列模型和注意力机制（Sequence models & Attention mechanism）"}]},{"id":"-Le0cOkveMZWvHlKgPtu","title":"3.2 选择最可能的句子（Picking the most likely sentence）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/32-xuan-ze-zuike-neng-de-ju-zi-ff08-picking-the-most-likely-sentence","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第三周 序列模型和注意力机制（Sequence models & Attention mechanism）"}]},{"id":"-Le0cOkwb-x5OwddQtJg","title":"3.3 集束搜索（Beam Search）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/33-ji-shu-sou-suo-ff08-beam-search","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第三周 序列模型和注意力机制（Sequence models & Attention mechanism）"}]},{"id":"-Le0cOkxS1pb0GWsKBJr","title":"3.4 改进集束搜索（Refinements to Beam Search）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/34-gai-jin-ji-shu-sou-suo-ff08-refinements-to-beam-search","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第三周 序列模型和注意力机制（Sequence models & Attention mechanism）"}]},{"id":"-Le0cOkyXd7Iy_BGA_JB","title":"3.5 集束搜索的误差分析（Error analysis in beam search）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/35-ji-shu-sou-suode-wu-cha-fen-xi-ff08-error-analysis-in-beam-search","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第三周 序列模型和注意力机制（Sequence models & Attention mechanism）"}]},{"id":"-Le0cOkzEtst0YwOUD6G","title":"3.6 Bleu 得分（选修）（Bleu Score (optional)）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/36-bleu-de-fen-ff08-xuan-xiu-ff09-ff08-bleu-score-optional","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第三周 序列模型和注意力机制（Sequence models & Attention mechanism）"}]},{"id":"-Le0cOl--7O3QDrL4Ucn","title":"3.7 注意力模型直观理解（Attention Model Intuition）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/37-zhu-yi-li-mo-xing-zhi-guan-li-jie-ff08-attention-model-intuition","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第三周 序列模型和注意力机制（Sequence models & Attention mechanism）"}]},{"id":"-Le0cOl0pjrrlITp5I1N","title":"3.8注意力模型（Attention Model）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/38zhu-yi-li-mo-xing-ff08-attention-model","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第三周 序列模型和注意力机制（Sequence models & Attention mechanism）"}]},{"id":"-Le0cOl14tKTry-mOcwq","title":"3.9语音识别（Speech recognition）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/39yu-yin-shi-bieff08-speech-recognition","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第三周 序列模型和注意力机制（Sequence models & Attention mechanism）"}]},{"id":"-Le0cOl2WSnbj1jpgFcO","title":"3.10触发字检测（Trigger Word Detection）","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/310hong-fa-zi-jian-ce-ff08-trigger-word-detection","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第三周 序列模型和注意力机制（Sequence models & Attention mechanism）"}]},{"id":"-Le0cOl3j103mLVjUZ8N","title":"Neural machine translation with attention","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/neural-machine-translation-with-attention-v4","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第三周 序列模型和注意力机制（Sequence models & Attention mechanism）"}]},{"id":"-Le0cOl4S0NV7eOd1lTQ","title":"nmt_utils.py","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/nmtutils-py","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第三周 序列模型和注意力机制（Sequence models & Attention mechanism）"}]},{"id":"-Le0cOl556q-ylTLQ47V","title":"Trigger word detection","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/trigger-word-detection-v1","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第三周 序列模型和注意力机制（Sequence models & Attention mechanism）"}]},{"id":"-Le0cOl6OOKwWcAHGpj3","title":"td_utils.py","pathname":"/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/tdutils-py","siteSpaceId":"sitesp_CQZZK","description":"","breadcrumbs":[{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第五门课 序列模型(Sequence Models)"},{"label":"第三周 序列模型和注意力机制（Sequence models & Attention mechanism）"}]}]}