[Stats385] Lecture 01-02, warm up with some questions
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)
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。
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?
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
- 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 ...
- 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 ...
- [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 ...
- 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 ...
- [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 ...
- [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 ...
- Cheatsheet: 2016 02.01 ~ 02.29
Web How to do distributed locking Writing Next Generation Reusable JavaScript Modules in ECMAScript ...
- Cheatsheet: 2015.02.01 ~ 02.28
Other API Best Practices: API Management Rewriting History with Git Rebase .NET Announcing Microsoft ...
- 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
- aps.net手写验证模型的方法
/// <summary> /// 基础验证类 /// </summary> public class BaseValidator { /// <summary> ...
- Raspberry Pi GPIO Protection
After damaging the GPIO port on our raspberry pi while designing a new solar monitoring system we de ...
- EBS 由数据库端找到对应的前台URL地址
SELECT home_url FROM icx_parameters; SELECT profile_option_value FROM fnd_profile_option_values ...
- Android 创建单独的服务运行在后台(无界面)
转自:https://blog.csdn.net/a704225995/article/details/56481934 今天项目有个需求是,开启一个服务单独运行在后台,而且还不能有界面,在度娘搜索了 ...
- [CGAL]带岛多边形三角化
CGAL带岛多边形三角化,并输出(*.ply)格式的模型 模型输出的关键是节点和索引 #include <CGAL/Triangulation_vertex_base_with_id_2.h&g ...
- shell命令行执行python(解析json)
每个脚本都有自己的擅长. 有次实现一个work,使用了shell,php,python看着文件种类多,不方便交接,看着也比较麻烦. 减少文件种类数,也是很有必要的. 遇到的场景:shell程序需要从j ...
- Redis更新的正确方法
原文(缓存更新的套路):看到好些人在写更新缓存数据代码时,先删除缓存,然后再更新数据库,而后续的操作会把数据再装载的缓存中.然而,这个是逻辑是错误的.试想,两个并发操作,一个是更新操作,另一个是查询操 ...
- CentOS6.9下安装python notebook
操作系统:CentOS6.9_x64 python版本 : python2.7.13 添加低权限新用户: useradd mike su mike 使用virtualenv安装python2.7环境 ...
- Spring4学习笔记二:Bean配置与注入相关
一:Bean的配置形式 基于XML配置:在src目录下创建 applicationContext.xml 文件,在其中进行配置. 基于注解配置:在创建bean类时,通过注解来注入内容.(这个不好,因 ...
- js获取过滤条件中参数的快捷方式
// window.location.href = "topupRecordController.do?exportExcel&" + encodeURI($(" ...