1.6 dropout 正则化(Dropout Regularization)
Previous1.5 为什么正则化有利于预防过拟合呢?(Why regularization reduces overfitting?)Next1.7 理解 dropout(Understanding Dropout)
Last updated
Last updated
dl = np.random.rand(al.shape[0],al.shape[1])<keep_probal = np.multiply(al,dl)al /= keep_prob