Skip to content

wycjl/CS231n

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

66 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🐹 CS231n


Term one Schedual :

Subject Hours Notes
Lecture 1 Done Done Done Done Done Done Done Video 1h
Lecture 2 Done Done Done Done Done Done Done Python/Numpy tutorial 2h
Done Done Done Done Done Done Done Image Classigication 1h
Done Done Done Done Done Done Done Linear Classification (1/2) 1h
Done Done Done Done Done Done Done Video 1h
Done Done Done Done Done Done Done Q1 3h 10月21日 截止
Lecture 3 Done Done Done Done Done Done Done Linear Classification (2/2) 1h
Done Done Done Done Done Done Done Optimization Notes 2h
Done Done Done Done Done Done Video 2h
Done Done Done Done Done Q2 4h
Lecture 4 Done Done Done Done Done Backprop notes 2h
Done Done Done Done Linear Backprop exa 2h 10月28日 截止
Done Done Done Done Done Video 1h
Done Optional Reading 10h
Done Done Q3 3h
Lecture 5 Done Done ConvNet notes 3h
Done Done Video 1h
Q4 4h 11月4日 截止
Lecture 6 Done CNN 1 1h
Done CNN 2 2h
Done CNN 3 2h
Optional Reading 9h
Done Video 1h
Q5 2h
Q6 (opt) 1h 11月11日 截止
Summary Unit 1 42h

  • 我们参照 Stanford Honor Code ,简而言之就是作业过程中可以讨论算法,但自己实现前不可以看别人的代码

  • 讨论组:

    • Blog No.1 (这里有其他同学的解法,谨慎浏览,做完作业后可以来交流解法)
    • Blog No.2

Deep Learning Books

  • Hands on Tensorflow ----- 亚马逊评分4.7 作者是Youtube视频分类的负责人,作业非常棒,第9章开始是深度学习

  • Deep Learning —— 亚马逊评分4.5,第一本系统介绍深度学习理论的书,作者是GAN发明人,建议做两个项目后再看,否则不好get他的点

  • Neural Network and Deep Learning —— 非常好的入门课本,培养sense用,有很多能把玩的程序,直观感受为什么神经网络可以拟合任何函数 [大概20h看完]

Python:

  • Design of Computer Programs —— 人工智能领域大神 Peter Novig 讲的课,很有挑战性,课上的实现都相当巧妙 [大概50h看完]

Papers:

  • [A Few Useful Things to Know about Machine Learning.pdf](共享文件/A Few Useful Things to Know about Machine Learning.pdf)

    (These include pitfalls to avoid, important issues to focus on, and answers to common questions.)

  • 我们预计12月30日完成全部课程;)

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 87.6%
  • HTML 10.7%
  • Python 1.7%