Theories of Deep Learning

借该课程,进入战略要地的局部战斗中,采用红色字体表示值得深究的概念,以及想起的一些需要注意的地方。

Lecture 01

Lecture01: Deep Learning Challenge. Is There Theory? (Donoho/Monajemi/Papyan)

Video link

纯粹的简介,意义不大。


Lecture 02

Video: Stats385 - Theories of Deep Learning - David Donoho - Lecture 2

资料:http://deeplearning.net/reading-list/ 【有点意思的链接】

Readings for this lecture

1 A mathematical theory of deep convolutional neural networks for feature extraction
2 Energy propagation in deep convolutional neural networks
3 Discrete deep feature extraction: A theory and new architectures
4 Topology reduction in deep convolutional feature extraction networks

重要点记录:

未知概念:能量传播,Topology reduction

Lecturer said: 

"Deep learning is simply an era where brute force has sudenly exploded its potential."

"How to use brute force (with limited scope) methold to yield result."

介绍ImageNet,没啥可说的;然后是基本back-propagation。

提了一句:

Newton法的发明人牛顿从来没想过用到NN这种地方,尬聊。

output的常见输出cost计算【补充】,介绍三种:

Assume z is the actual output and t is the target output.

squared error: E = (z-t)2/2
cross entropy: E = -t log(z) - (1-t)log(1-z)
softmax: E = -(zi - log Σj exp(zj)), where i is the correct class.

第一个难点:

严乐春大咖:http://yann.lecun.com/exdb/publis/pdf/lecun-88.pdf

通过拉格朗日不等式认识反向传播,摘自论文链接前言。

开始介绍常见的卷积网络模型以及对应引进的feature。

讲到在正则方面,dropout有等价ridge regression的效果。

在损失函数中,weight decay是放在正则项(regularization)前面的一个系数,
正则项一般指示模型的复杂度,所以weight decay的作用是调节模型复杂度对损失函数的影响,
若weight decay很大,则复杂的模型损失函数的值也就大。
第二个难点:

通过这个对比:AlexNet vs. Olshausen and Field 引出了一些深度思考:

  • Why does AlexNet learn filters similar to Olshausen/Field?
  • Is there an implicit sparsity-promotion in training network?
  • How would classification results change if replace learned filters in first layer with analytically defined wavelets, e.g. Gabors?
  • Filters in the first layer are spatially localized, oriented and bandpass. What properties do filters in remaining layers satisfy?
  • Can we derive mathematically?
这些内容貌似在之后的lecture展开,在此作下标记。
Ref reading:sparse codingpaper
 
 
Batch Normalization: 

 
其中有提出这么一个问题,甚是有趣:

Does this imply filters can be learned in unsupervised manner?

第三个难点:

关于卷积可视化,以及DeepDream的原理。

第四个难点:

补充一个难点:权重初始化的策略


Links:

以上提及的重难点,未来将在此附上对应的博客链接。

[Stats385] Lecture 01-02, warm up with some questions的更多相关文章

  1. linux下生成00 01 02..99的这些数

    [root@localhost ~]# seq -s " " -w 9901 02 03 04 05 06 07 08 09 10 11 12 13 14 15 16 17 18 ...

  2. ML Lecture 0-1: Introduction of Machine Learning

    本博客是针对李宏毅教授在Youtube上上传的课程视频<ML Lecture 0-1: Introduction of Machine Learning>的学习笔记.在Github上也po ...

  3. [Stats385] Lecture 03, Harmonic Analysis of Deep CNN

    大咖秀,注意提问环节大家的表情,深入窥探大咖的心态,很有意思. 之前有NG做访谈,现在这成了学术圈流行. Video: https://www.youtube.com/watch?v=oCohnBbm ...

  4. CS229 Lecture 01

    CS229 Lecture notes 01 机器学习课程主要分为4部分:监督学习:学习理论:无监督学习:增强学习. $x^{(i)}$表示特征,$y^{(i)}$表示目标,$i=1...m$.m是训 ...

  5. [Stats385] Lecture 04: Convnets from Probabilistic Perspective

    本篇围绕“深度渲染混合模型”展开. Lecture slices Lecture video Reading list A Probabilistic Framework for Deep Learn ...

  6. [Stats385] Lecture 05: Avoid the curse of dimensionality

    Lecturer 咖中咖 Tomaso A. Poggio Lecture slice Lecture video 三个基本问题: Approximation Theory: When and why ...

  7. Cheatsheet: 2016 02.01 ~ 02.29

    Web How to do distributed locking Writing Next Generation Reusable JavaScript Modules in ECMAScript ...

  8. Cheatsheet: 2015.02.01 ~ 02.28

    Other API Best Practices: API Management Rewriting History with Git Rebase .NET Announcing Microsoft ...

  9. Cheatsheet: 2014 02.01 ~ 02.28

    Database Managing disk space in MongoDB When to use GridFS on MongoDB .NET The Past, Present, and Fu ...

随机推荐

  1. 安装 jenkins

    1. 将jenkins.war包放在 tomcat  的 webapps 目录下即可 2 重启 tomcat 3. 通过浏览器访问 IP:8080/jenkins

  2. 吴伯凡:VUCA时代的自我迭代

    吴伯凡:VUCA时代的自我迭代 https://mp.weixin.qq.com/s?src=3&timestamp=1506588223&ver=1&signature=nv ...

  3. WinPython

    WinPython   http://winpython.github.io/

  4. 总结&#183;展望

    学了算法也有半年了.也是学期末,确实是该总结了.半年来说不上多努力,毕竟不如高中那时候早晨5点起晚上12点睡,但也确实学到不少东西(尽管眼下来说根本用不到并且我也不确定以为会不会去用.毕竟专业放在那里 ...

  5. Delphi 中big5 转 Unicode 函数

    function Big5ToUnicode(str Char): widestring; var len: integer; begin len:=MultiByteToWideChar(,,PCh ...

  6. 从零开始优雅的使用mongodb实例

    基本连接 一.创建express工程testmon express testmon 二.精简app.js var express = require("express"); var ...

  7. mysql5.7报err 1055错误 sql_mode=only_full_group_by

    vim /etc/my.cnf 末尾增加 sql_mode='STRICT_TRANS_TABLES,NO_ZERO_IN_DATE,NO_ZERO_DATE,ERROR_FOR_DIVISION_B ...

  8. Mybatis Dynamic Query 更新

    文章目录 1. 简介 2. 准备工作 3. 开始更新 3.1. update 3.2. update Null 4. 结束 5. 关注@我 项目地址:https://github.com/wz2coo ...

  9. Idea调试

    Idea调试 学习了:https://www.jb51.net/article/128965.htm 1,多线程同时断点: 2,drop frame 回退调试: 3,条件断点/片段代码: 4,调试的时 ...

  10. app:processDebugResources

    org.gradle.api.tasks.TaskExecutionException: Execution failed for task ':app:processDebugResources'. ...