[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
- springmvc框架javax.servlet.http.HttpServletResponse出现小红叉
需要在项目点右键配置属性--->Library--->server runtime--->但是配置不能成功,原因是没有在windows下配置过runtime environment, ...
- 喵哈哈村的魔法考试 Round #14 (Div.2) 题解
喵哈哈村的四月半活动(一) 题解: 唯一的case,就是两边长度一样的时候,第三边只有一种情况. #include <iostream> #include <cstdio> # ...
- react-native开源组件react-native-wechat学习
转载链接:http://www.ncloud.hk/%E6%8A%80%E6%9C%AF%E5%88%86%E4%BA%AB/react-native-open-source-components-r ...
- 解决无法安装Flash Player的问题
1.同时搜索几个关键词:关键词用空格分开,例如:“中国 历史”会搜索显示同时包含中国.历史两个词的网页 2.排除某个关键词:被排除的词前面加上-号,例如“中国 历史 -清朝”会把有清朝两个字的网页过滤 ...
- Install windows server 2008 on ESXi 5.1, add to domain and config for remote desktop
Never give up ---xingyunpi Install windows server 2008 system on ESXi 5.1, add it to a domain and do ...
- EasyUI使用技巧总结
combobox组件 一.禁用combobox里面的输入框 $("选择器").combo('textbox').attr("readonly", "r ...
- c++设计一个无法被继承的类
要求是该类不能被继承,但是能够像正常的类一样使用.那么一下方法就不符合题目要求: 1.构造函数和析构函数设置为private.这样就不能定义一个类的实例 2.类似于singleton模式那样,定义一个 ...
- Failed to configure a DataSource: 'url' attribute is not specified and no embedded datasource could be configured.
SpringBoot项目编译成功,启动报错 提示信息很明显,通过查看依赖关系,可以找到原因 导致这个问题的原因是因为,在 pom.xml 配置文件中,配置了数据连接技术 spring-boot-sta ...
- 阿里云centos安装docker-engine实践
近日在阿里云ECS服务器(centos系统)中安装docker,参考官方指南 https://docs.docker.com/engine/installation/linux/centos/ 大概 ...
- fft ocean注解
针对这两篇教程: http://www.keithlantz.net/2011/10/ocean-simulation-part-one-using-the-discrete-fourier-tran ...