CNN卷积神经网络入门

cs231n用于视觉识别的卷积神经网络：

http://cs231n.github.io/convolutional-networks/

Neural Networks and Deep Learning在线阅读链接：
http://neuralnetworksanddeeplearning.com/chap1.html

卷积神经网络入门文章：

https://adeshpande3.github.io/adeshpande3.github.io/A-Beginner’s-Guide-To-Understanding-Convolutional-Neural-Networks/

ReLU（修正线性单元）层：

参见 Geoffrey Hinton（即深度学习之父）的论文：Rectified Linear Units Improve Restricted Boltzmann Machines

Dropout层：

参考 Geoffrey Hinton 的论文：
Dropout: A Simple Way to Prevent Neural Networks from Overfitting

网络层中的网络

参阅 Min Lin 的论文：Network In Network

迁移学习

Yoshua Bengio （另外一个深度学习先驱 ）论文：How transferable are features in deep neural networks?Ali Sharif Razavian 论文：CNN Features off-the-shelf: an Astounding Baseline for Recognition Jeff Donahue 论文：DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition