# 第三门课 结构化机器学习项目（Structuring Machine Learning Projects） - [第一周 机器学习（ML）策略（1）（ML strategy（1））](https://baozoulin.gitbook.io/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.md) - [1.1 为什么是 ML 策略？（Why ML Strategy?）](https://baozoulin.gitbook.io/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.md) - [1.2 正交化（Orthogonalization）](https://baozoulin.gitbook.io/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.md) - [1.3 单一数字评估指标（Single number evaluation metric）](https://baozoulin.gitbook.io/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.md) - [1.4 满足和优化指标（Satisficing and optimizing metrics）](https://baozoulin.gitbook.io/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.md) - [1.5 训练/开发/测试集划分（Train/dev/test distributions）](https://baozoulin.gitbook.io/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.md) - [1.6 开发集和测试集的大小（Size of dev and test sets）](https://baozoulin.gitbook.io/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.md) - [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）](https://baozoulin.gitbook.io/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.md) - [1.8 为什么是人的表现？（ Why human-level performance?）](https://baozoulin.gitbook.io/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.md) - [1.9 可避免偏差（Avoidable bias）](https://baozoulin.gitbook.io/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.md) - [1.10 理解人的表现（Understanding human-level performance）](https://baozoulin.gitbook.io/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.md) - [1.11 超过人的表现（Surpassing human- level performance）](https://baozoulin.gitbook.io/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.md) - [1.12 改善你的模型的表现（Improving your model performance）](https://baozoulin.gitbook.io/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.md) - [第二周：机器学习策略（2）(ML Strategy (2))](https://baozoulin.gitbook.io/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.md) - [2.1 进行误差分析（Carrying out error analysis）](https://baozoulin.gitbook.io/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.md) - [2.2 清楚标注错误的数据（Cleaning up Incorrectly labeled data）](https://baozoulin.gitbook.io/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.md) - [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）](https://baozoulin.gitbook.io/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.md) - [2.4 在不同的划分上进行训练并测试（Training and testing on different distributions）](https://baozoulin.gitbook.io/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.md) - [2.5 不匹配数据划分的偏差和方差（Bias and Variance with mismatched data distributions）](https://baozoulin.gitbook.io/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.md) - [2.6 定位数据不匹配（Addressing data mismatch）](https://baozoulin.gitbook.io/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.md) - [2.7 迁移学习（Transfer learning）](https://baozoulin.gitbook.io/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.md) - [2.8 多任务学习（Multi-task learning）](https://baozoulin.gitbook.io/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.md) - [2.9 什么是端到端的深度学习？（What is end-to-end deep learning?）](https://baozoulin.gitbook.io/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.md) - [2.10 是否要使用端到端的深度学习？（Whether to use end-to-end learning?）](https://baozoulin.gitbook.io/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.md) --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://baozoulin.gitbook.io/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.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.