1. 经典论文阅读 -- AlexNet

阅读总结

AlexNet是深度学习浪潮的奠基作之一，发表在 2012 年. 不管是看博客，还是分享的文章，都不如直接阅读论文本身，论文是作者毫不保留的拍给你~

作者：

0. Abstract

我做了啥，是什么效果，靠什么达到了这个效果.

1. Introduction

In the end, the network’s size is limited mainly by the amount of memory available on current GPUs and by the amount of training time that we are willing to tolerate. Our network takes between five and six days to train on two GTX 580 3GB GPUs. All of our experiments suggest that our results can be improved simply by waiting for faster GPUs and bigger datasets to become available.

3. The Architecture

The architecture of our network is summarized in Figure 2.

最后变成一个 4096 向量机器能懂的，可以理解为一个压缩，通过中间的模型。

4. Reducing Overfitting

–给你一些题，你就把他背下来，你考试肯定考不好。

5 Details of learning

We trained the network for roughly 90 cycles through the
training set of 1.2 million images, which took five to six days on two NVIDIA GTX 580 3GB GPUs.

Nvdia算力 和 算法一并提升。

6 Results

6.1 Qualitative Evaluations

神经网络的定性评估

神经网络的学习，到底是去学一个东西的形状、纹理呢，还是学一个状态呢？当前是不可解释的 – 神经网络当前大家仍然是不知道它到底在学习什么，可解释性一直是大家诟病的地方。

7. Discussion