Review08 [coursera] Machine learning - Stanford University - Andrew Ng

MoMo_qyc

于 2019-04-27 11:47:10 发布

阅读量238

点赞数 1

CC 4.0 BY-SA版权

分类专栏： course assignment 文章标签： Machine Learning

本文链接：https://blog.youkuaiyun.com/MoMo_flamboyant/article/details/89599694

course 同时被 2 个专栏收录

40 篇文章

订阅专栏

assignment

33 篇文章

订阅专栏

本文探讨了神经网络的学习过程及调试策略，强调了反向传播算法的重要性，并指出在确保代码无误后，应禁用梯度检查以提高计算效率。文章还讨论了使用梯度下降训练神经网络时可能遇到的局部最优解问题，以及如何通过绘制代价函数J(Θ)随迭代次数变化的曲线来检查算法是否正常工作。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Neural Networks: Learning

For computational efficiency, after we have performed gradient checking to verify that our backpropagation code is correct, we usually disable gradient checking before using backpropagation to train the network. T

Using gradient checking can help verify if one's implementation of backpropagation is bug-free. T

Suppose you are training a neural network using gradient descent. Depending on your random initialization, your algorithm may converge to different local optima (i.e., if you run the algorithm twice with different random initializations, gradient descent may converge to two different solutions). T

If we are training a neural network using gradient descent, one reasonable "debugging" step to make sure it is working is to plot J(Θ) as a function of the number of iterations, and make sure it is decreasing (or at least non-increasing) after each iteration. T