http://videolectures.net,例如输入Zoubin
Coursera
Machine learning
https://class.coursera.org/ml-005/lecture/preview#/ml-005/lecture
I. Introduction (Week 1): watch more than twice (能闭目听懂,绝不再看)
II. Linear Regression with One Variable (Week 1):已看一次,内容很容易,都已理解
III. Linear Algebra Review (Week 1, Optional):绝不看,都是基本内容
IV. Linear Regression with Multiple Variables (Week 2)和Lecture6 Logistic Regression (Week 3), Lecture7 Regularization (Week 3), Lecture8 Neural Networks Representation (Week 4), Lecture10 Advice for Applying Machine Learning (Week 6), Lecture11 Machine Learning System Design (Week 6), Lecture17 Large Scale Machine Learning (Week 10)已看两次,内容很容易,都已理解。Lecture9 Neural Networks Learning (Week 5)已看两次
Lecture5 Octave Tutorial暂不看(百度百科:Octave是一种高级语言,主要设计用来进行数值计算,它是MathWorks出品的Matlab商业软件的一个强有力的竞争产品。)
20150814将Lecture7 Regularization (Week 3)之前都已经复习两次,并且整理出复习提纲。20150830和20150904将Lecture 10分别复习一次,绝不再看。20150904和20150912将Lecture 11和Lecture 17分别复习一次,绝不再看。
下面看
京: support vector machines绝对绝对先自己回忆,再看以前笔记,如果课件全懂,绝不看;clustering和Dimensionality Reduction,如果课件全懂,绝不看;这三部分一定得先看以前的模式笔记。
肥: Anomaly Detection, Recommender Systems和Lecture18 暂不看,因为我不研究这些,最后所有内容都看完了再看
一次没看
已看一次,再看一次。之前内容已看两次,内容很容易,都已理解,绝不再看
学法:先看无字幕版,再看有字幕版,每个最少最少看两篇,直至闭目听懂。 一定认真听记笔记,很多课程都仅听一次
韩家炜教授数据挖掘龙星课程视频
http://www.youku.com/playlist_show/id_1903290.html
韩家炜教授Pattern Discovery in Data Mining
https://www.coursera.org/course/patterndiscovery
Si Liu老师在VALSE20150813-Panel推荐的Boyd的Convex Optimization课程 http://www.youtube.com/watch?v=McLq1hEq3UY; http://stanford.edu/~boyd/cvxbook/。一个是视频,一个是video
Mingming Chen(Nankai) recomm end a co urse in Va lse QQ群: 牛津大学机器学习课程(P PT,讲课 视频,作业,代码等): https://www.cs.ox.ac.uk/people/nando.defreitas/machinele arning/
Fei-Fei Li: How we're teaching computers to understand pictures
Coursera
Machine learning
https://class.coursera.org/ml-005/lecture/preview#/ml-005/lecture
I. Introduction (Week 1): watch more than twice (能闭目听懂,绝不再看)
II. Linear Regression with One Variable (Week 1):已看一次,内容很容易,都已理解
III. Linear Algebra Review (Week 1, Optional):绝不看,都是基本内容
IV. Linear Regression with Multiple Variables (Week 2)和Lecture6 Logistic Regression (Week 3), Lecture7 Regularization (Week 3), Lecture8 Neural Networks Representation (Week 4), Lecture10 Advice for Applying Machine Learning (Week 6), Lecture11 Machine Learning System Design (Week 6), Lecture17 Large Scale Machine Learning (Week 10)已看两次,内容很容易,都已理解。Lecture9 Neural Networks Learning (Week 5)已看两次
Lecture5 Octave Tutorial暂不看(百度百科:Octave是一种高级语言,主要设计用来进行数值计算,它是MathWorks出品的Matlab商业软件的一个强有力的竞争产品。)
20150814将Lecture7 Regularization (Week 3)之前都已经复习两次,并且整理出复习提纲。20150830和20150904将Lecture 10分别复习一次,绝不再看。20150904和20150912将Lecture 11和Lecture 17分别复习一次,绝不再看。
下面看
京: support vector machines绝对绝对先自己回忆,再看以前笔记,如果课件全懂,绝不看;clustering和Dimensionality Reduction,如果课件全懂,绝不看;这三部分一定得先看以前的模式笔记。
肥: Anomaly Detection, Recommender Systems和Lecture18 暂不看,因为我不研究这些,最后所有内容都看完了再看
一次没看
已看一次,再看一次。之前内容已看两次,内容很容易,都已理解,绝不再看
学法:先看无字幕版,再看有字幕版,每个最少最少看两篇,直至闭目听懂。 一定认真听记笔记,很多课程都仅听一次
韩家炜教授数据挖掘龙星课程视频
http://www.youku.com/playlist_show/id_1903290.html
韩家炜教授Pattern Discovery in Data Mining
https://www.coursera.org/course/patterndiscovery
Si Liu老师在VALSE20150813-Panel推荐的Boyd的Convex Optimization课程 http://www.youtube.com/watch?v=McLq1hEq3UY; http://stanford.edu/~boyd/cvxbook/。一个是视频,一个是video
Mingming Chen(Nankai) recomm end a co urse in Va lse QQ群: 牛津大学机器学习课程(P PT,讲课 视频,作业,代码等): https://www.cs.ox.ac.uk/people/nando.defreitas/machinele arning/
Fei-Fei Li: How we're teaching computers to understand pictures
http://www.ted.com/talks/fei_fei_li_how_we_re_teaching_computers_to_understand_pictures#
[转自静.沙龙]斯坦福人工智能实验室主任、计算机视觉实验室主任Fei-Fei Li教授本月的计算机视觉TED Talk: http://t.cn/RAwE22v 不错的科普教材。
美国大学线上课件大全: http://mp.weixin.qq.com/s?__biz=MzA5NzcxMzc4OQ==&mid=214275160&idx=2&sn=6e1377d47db154eb7507c6eac6f4ad26&scene=1&from=groupmessage&isappinstalled=0#rd
徐亦达老师机器学习视频网站
http://www.valser.org/thread-725-1-1.html http://www-staff.it.uts.edu.au/~ydxu/statistics.htm Valse qq群有人说:
http://www.valser.org/thread-725-1-1.html http://www-staff.it.uts.edu.au/~ydxu/statistics.htm Valse qq群有人说:
徐老师 讲的很仔细