# 图解CNN：通过100张图一步步理解CNN

## 图解CNN：通过100张图一步步理解CNN

LeNet-5

Classfication

【icml09 - Convolutional Deep Belief Networks.pdf】

【Playing Atari with Deep Reinforcement Learning】

【Robot Learning Manipulation Action Plans】

A toy ConvNet：X’s and O’s

Features

Convolution

Pooling

CNN中使用的另一个有效的工具被称为“池化(Pooling)”。池化可以将一幅大的图像缩小，同时又保留其中的重要信息。池化背后的数学顶多也就是小学二年级水平。它就是将输入图像进行缩小，减少像素信息，只保留重要信息。通常情况下，池化都是2*2大小，比如对于max-pooling来说，就是取输入图像中2*2大小的块中的最大值，作为结果的像素值，相当于将原始图像缩小了4倍(注：同理，对于average-pooling来说，就是取2*2大小块的平均值作为结果的像素值)。

Normalization

![][01]
[01]:http://latex.codecogs.com/png.latex?f(x) = max(0, x)

Deep Learning

【综合上述所有结构】

Hyperparameters

Application

If you'd like to dig deeper into deep learning, check out my Demystifying Deep Learning post. I also recommend the notes from the Stanford CS 231 course by Justin Johnson and Andrej Karpathy that provided inspiration for this post, as well as the writings of Christopher Olah, an exceptionally clear writer on the subject of neural networks.

If you are one who loves to learn by doing, there are a number of popular deep learning tools available. Try them all! And then tell us what you think.
Caffe
CNTK
Deeplearning4j
TensorFlow
Theano
Torch
Many others

I hope you've enjoyed our walk through the neighborhood of Convolutional Neural Networks. Feel free to start up a conversation.

Brandon Rohrer

Reference：
http://brohrer.github.io/how_convolutional_neural_networks_work.html