[CS231n-CNN] Backpropagation(反向传播算法)

课程主页:http://cs231n.stanford.edu/

上节讲到loss function:

[CS231n-CNN] Backpropagation(反向传播算法)

引出了求导数使得loss function减小。

-Back Propagation :梯度下降+链式求导法则:

[CS231n-CNN] Backpropagation(反向传播算法)

这节的课件讲的比较细,先引用一下其他资源:

1.http://galaxy.agh.edu.pl/~vlsi/AI/backp_t_en/backprop.html

2.http://colah.github.io/posts/2015-08-Backprop/

[CS231n-CNN] Backpropagation(反向传播算法)

[CS231n-CNN] Backpropagation(反向传播算法)

[CS231n-CNN] Backpropagation(反向传播算法)

[CS231n-CNN] Backpropagation(反向传播算法)

[CS231n-CNN] Backpropagation(反向传播算法)

[CS231n-CNN] Backpropagation(反向传播算法)

[CS231n-CNN] Backpropagation(反向传播算法)

[CS231n-CNN] Backpropagation(反向传播算法)

[CS231n-CNN] Backpropagation(反向传播算法)

[CS231n-CNN] Backpropagation(反向传播算法)

[CS231n-CNN] Backpropagation(反向传播算法)

[CS231n-CNN] Backpropagation(反向传播算法)

[CS231n-CNN] Backpropagation(反向传播算法)

[CS231n-CNN] Backpropagation(反向传播算法)

[CS231n-CNN] Backpropagation(反向传播算法)

[CS231n-CNN] Backpropagation(反向传播算法)

 

矩阵运算:

[CS231n-CNN] Backpropagation(反向传播算法)

ps:!不代表阶乘

[CS231n-CNN] Backpropagation(反向传播算法)

[CS231n-CNN] Backpropagation(反向传播算法)

[CS231n-CNN] Backpropagation(反向传播算法)

 

上一篇:Django 2.0 学习(12):Django 模板语法


下一篇:解决You are using pip version 10.0.1, however version 18.1 is available. You should consider upgrading via the 'python -m pip install --upgrade pip' command.