CNN 入门学习资料整理

建议按序阅读

1. Convolutional Neural Networks卷积神经网络:

http://blog.csdn.net/zouxy09/article/details/8781543

2. Deep learning：三十八(Stacked CNN简单介绍):

http://www.cnblogs.com/tornadomeet/archive/2013/05/05/3061457.html

3. 深度学习（卷积神经网络）一些问题总结

http://blog.csdn.net/nan355655600/article/details/17690029

4. Notes on Convolutional Neural Networks:

http://cogprints.org/5869/

5. 基础的CNN分类模型及基本操作

ImageNet Classification with Deep Convolutional Neural Networks:

http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks

参考资料：ImageNet Classification with deep convolutional neural networks - 家家的专栏 - 博客频道 - CSDN

caffe : http://caffe.berkeleyvision.org/

6. 一种基于CNN的图像超分辨率重构方法：输出不是label是目标类型图像

Image Super-Resolution Using Deep Convolutional Networks

7. 扩展阅读

一种常用的深度CNN的网络结构 VGG

Very Deep Convolutional Networks for Large-Scale Image Recognition

残差网络

Deep residual learning for image recognition

分形网络（子网络与drop-path）

FractalNet: Ultra-Deep Neural Networks without Residuals

返卷积网络及特征可视化技术

Adaptive Deconvolutional Networks for Mid and High Level Feature Learning

特征可视化来辅助网络调优

Visualizing and Understanding Convolutional Networks.

属性中间节点的分布分析

On the Relationship between Visual Attributes and Convolutional Networks

基于CNN判别性学习结果的视频发现

A Discriminative CNN Video Representation for Event Detection

基于时空融合（多种）与多分辨率加速的处理chips（几个邻接frames）的CNN

Large-scale Video Classification with Convolutional Neural Networks

8. 特征逐层可视化 ipython notebook

http://nbviewer.ipython.org/github/BVLC/caffe/blob/master/examples/00-classification.ipynb