除了吴恩达的cs229之外,Bishop的《Pattern Recognition and Machine Learning》也是ML领域的经典书籍。
Christopher Michael Bishop,1959年生,牛津大学本科+爱丁堡大学博士。爱丁堡大学教授。英国皇家学会会员。
中文版:
https://www.gitbook.com/book/mqshen/prml/details
PRML的python实现:
https://github.com//ctgk/PRML
PRML的matlab实现:
https://github.com/PRML/PRMLT
秋季:CS106A
冬季:CS106B/X,CS109
春季:CS103,CS107
秋季:CS221,CS131,统计信息202
冬季:CS124,CS161
春季:CS231N,CS110
秋季:CS229
冬季:CS228,CS224N
春季:CS224W
秋季:CS238
冬季:CS246,CS234
https://github.com/prakhar1989/awesome-courses
精品课程大全集
https://github.com/kmario23/deep-learning-drizzle/blob/master/README.md
50+门《深度学习、强化学习、NLP、CV》课程超级大列表
https://mp.weixin.qq.com/s/tsidF_I5-QfaKUlX6Smtsg
这有300+门刚刚开课的编程计算机科学免费课程大集合
http://ufldl.stanford.edu/wiki/index.php/Main_Page
斯坦福的《Unsupervised Feature Learning and Deep Learning》教程,该网站本身就有中文翻译。
https://zhuanlan.zhihu.com/p/22038289
斯坦福CS231n课程(卷积神经网络,CNN)翻译。
https://mp.weixin.qq.com/s/TL15EgRfbIFnaOo6-SimfQ
斯坦福CS231n(李飞飞):卷积神经网络视觉识别课程讲义(完整版)
https://github.com/afshinea/stanford-cs-229-machine-learning
CS229小抄精华版
http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=MachineLearning
Andrew Ng的公开课视频。
https://web.stanford.edu/class/cs230/syllabus.html
CS230: Deep Learning。吴恩达2018年开的新课
https://stanford.edu/~shervine/teaching/cs-221/
学霸双胞胎开源斯坦福CS 221人工智能备忘录
这个教程以及下面的两个教程的作者是一对来自法国的学霸双胞胎,Afshine Amidi和Shervine Amidi。Afshine在MIT读完了硕士,目前是Uber的数据科学家。Shervine现在则是斯坦福硕士在读。
https://stanford.edu/~shervine/teaching/cs-230.html
CS230的Cheatsheet
https://github.com/afshinea/stanford-cs-230-deep-learning
CS230的Cheatsheet的PDF版本
http://www.cc.gatech.edu/~lsong/teaching/
佐治亚理工学院宋乐副教授的课件库。
http://web.cs.iastate.edu/~cs577/
Problem Solving Techniques for Applied Computer Science
https://onlinecourses.science.psu.edu/stat857/
Applied Data Mining and Statistical Learning
http://www.cs.unc.edu/~lazebnik/spring11/
Computer Vision
http://www.cnblogs.com/wei-li/archive/2012/03/24/2406404.html
网络公开课资源——关注CS/AI/Math
http://www.cs.columbia.edu/~blei/seminar/2016_discrete_data/index.html
Probabilistic Models of Discrete Data
http://mp.weixin.qq.com/s/dtg-alezht56mu_vOA4Lrg
14所世界顶级名校在线免费算法课程。这里的课程主要是非机器学习类的计算机算法。
http://mp.weixin.qq.com/s/qW_RZ–df6MjaKNgNdjeWA
10所世界顶级名校的25门在线免费机器学习课程!
https://lib-nuanxin.wqxuetang.com/
清华大学网上课程——文泉学堂
http://www.cs.cmu.edu/~tom/10701_sp11/lectures.shtml
CMU的Machine Learning
https://mp.weixin.qq.com/s/MlM39pbyr5G7Crgq0j4PGw
Bengio领衔:DeepMind、谷歌大脑核心研究员2017深度学习最新报告(该课程只适合有深度学习基础的人)
https://mp.weixin.qq.com/s/a5MBQqYCWmUMLpVXhOvg8Q
Yoshua Bengio深度学习暑期课程
https://mp.weixin.qq.com/s/CxKicJBvnk6FYWE4KuVmHw
二十六条深度学习经验,来自蒙特利尔深度学习
https://mp.weixin.qq.com/s/Bv1psJFFnZdYWW9reCbtrQ
2017年蒙特利尔深度学习暑期学校ppt分享
http://elmos.scripts.mit.edu/mathofdeeplearning/
Mathematical Aspects of Deep Learning
http://ciml.info/
马里兰大学的机器学习课程
http://mbmlbook.com/toc.html
Chris Bishop发布在线新书。Bishop 2007年的《Pattern Recognition And Machine Learning》一书绝对是经典之作,然而难度偏高。这本是入门级别的。
https://mp.weixin.qq.com/s/6XEUATgudV9AT7Y8FLfdlQ
台大林轩田:机器学习基石(全套65课中文视频)
http://yerevann.com/a-guide-to-deep-learning/
国外网红的深度学习指南
https://am207.github.io/2017/
哈佛课程:Advanced Scientific Computing: Stochastic Optimization Methods. Monte Carlo Methods for Inference and Data Analysis
https://www.deeplearning.ai/
吴恩达离开百度之后开设的DL教程
https://study.163.com/topics/deepLearning/
这是网易提供的deeplearning.ai课程的中文版
https://github.com/dformoso/machine-learning-mindmap
ML思维导图
https://github.com/dformoso/deeplearning-mindmap
DL思维导图
http://neuralnetworksanddeeplearning.com/
Michael Nielsen写的DL blog。
https://cs.nju.edu.cn/zlj/Courses.html
南京大学张利军:数据挖掘和优化
https://nndl.github.io/
复旦邱锡鹏(FudanNLP项目负责人):神经网络与深度学习
https://github.com/FudanNLP/nlp-beginner
复旦大学NLP入门教程
http://joanbruna.github.io/stat212b/
Stat 212b:Topics Course on Deep Learning——加州大学伯克利分校统计系Joan Bruna(Yann LeCun博士后)以统计的角度讲解DL。
https://blogs.princeton.edu/imabandit/orf523-the-complexities-of-optimization/
ORF 523: The complexities of optimization
https://cs.brown.edu/courses/csci1460
CSCI 1460: Introduction to Computational Linguistics
https://berkeley-deep-learning.github.io/
UCB的DL课程
http://web.cs.ucdavis.edu/~yjlee/teaching/ecs174-spring2017/
ECS 174: Computer Vision
http://web.cs.ucdavis.edu/~yjlee/teaching/ecs289g-fall2016/
ECS 289G: Visual Recognition
http://www.cs.jhu.edu/~misha/Fall04/
Seminar on Shape Analysis and Retrieval
http://info.usherbrooke.ca/hlarochelle/neural_networks/description.html
Hugo Larochelle: Online Course on Neural Networks
http://www.stat.cmu.edu/~larry/=sml/
CMU:Statistical Machine Learning 2016
http://www.stat.cmu.edu/~ryantibs/statml/
CMU:Statistical Machine Learning 2017
http://people.ece.umn.edu/users/parhi/slides.html
VLSI Digital Signal Processing Systems: Design and Implementation
https://stats385.github.io/
STATS 385:Theories of Deep Learning
http://www.cs.cmu.edu/~rsalakhu/10707/lectures.html
CMU:Deep Learning 2017
https://software.intel.com/en-us/ai-academy/students/kits
Intel提供的课程,包括ML和DL两门课程。
http://www.stats.ox.ac.uk/~teh/courses.html
Oxford的Yee Whye Teh提供的ML课程,偏统计方向。
https://mp.weixin.qq.com/s/iUmRZMpQJpaV4jNxmp-z4w
面向搜索的深度学习实战书籍和代码《Deep Learning for Search》
https://mp.weixin.qq.com/s/txT8qLxpQQ62DAPVS1NTDA
DeepMind深度学习最佳实践与新技术展望
http://lamda.nju.edu.cn/weixs/book/CNN_book.pdf
南京大学魏秀参:《解析卷积神经网络—深度学习实践手册》
https://agi.mit.edu/
MIT 6.S099: Artificial General Intelligence
http://deeplearning.cs.cmu.edu/spring2018.html
11-785 Introduction to Deep Learning
http://introtodeeplearning.com/
MIT 6.S191: Introduction to Deep Learning
http://3dvision.princeton.edu/courses.html
普林斯顿的DL课程
https://www.cs.princeton.edu/courses/catalog
普林斯顿的CS课程
http://www.cs.toronto.edu/~rgrosse/courses/csc321_2018/
多伦多大学CSC 321: Intro to Neural Networks and Machine Learning
http://www.math.pku.edu.cn/teachers/ganr/course/pr2010/
北京大学:模式识别
http://slazebni.cs.illinois.edu/spring17/
CS 598 LAZ: Cutting-Edge Trends in Deep Learning and Recognition。这是一门研究生的课程,很有深度和广度。
https://tianchi.aliyun.com/markets/tianchi/aiacademy
阿里发布免费深度学习课程
https://www.isip.piconepress.com/courses/msstate/ece_8443/index.html
ECE 8443: pattern recognition
https://www.isip.piconepress.com/courses/msstate/ece_8423/index.html
ECE 8423: adaptive signal processing
http://crcv.ucf.edu/courses/
UCF的系列Vision课程,其中的CAP 6412:Advanced Computer Vision是一门高级课程。
http://www.cs.tut.fi/~tabus/LSC.html
SGN-2306 Signal Compression
http://www.cs.tut.fi/~tabus/course/AdvSP.html
SGN 21006 Advanced Signal Processing
http://www.cs.cmu.edu/~me/811/mathfund.html
16-811: Math Fundamentals for Robotics
https://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-241j-dynamic-systems-and-control-spring-2011/
Dynamic Systems and Control
http://www.cs.tut.fi/~hehu/SSP/
SGN-2607 Statistical Signal Processing
http://web-static-aws.seas.harvard.edu/courses/cs281/
CS281: Advanced Machine Learning
https://cs.nyu.edu/~panozzo/ustc/
Robust Mesh Generation and Applications to Geometry Processing
https://cyclostationary.blog
Cyclostationary Signal Processing。这个是一个在信号处理领域使用统计学的blog。作者Chad Spooner,UCB本科(1986)+UCD博士(1992)。
https://mp.weixin.qq.com/s/150raN1kPc6c0pAB1DVLWw
118页概率思维教程——基础、技巧与算法
https://mp.weixin.qq.com/s/iPuP2WOcFTpO-EomfS6sjg
554页《统计关联性与概率编程》教程
https://mp.weixin.qq.com/s/c1M5R3AYhIpJX0MHmp52_g
246页《统计机器学习与凸优化》教程
https://mp.weixin.qq.com/s/OCjznxO1WjJnnryuK8uRTw
Scikit-learn作者之一可微分动态编程51页教程
https://mp.weixin.qq.com/s/LtmzL4nk-yS7G7zKv5jR8A
帝国理工学院134页机器学习中的数学知识
https://mp.weixin.qq.com/s/YVNuuH0yyZx0_L4ch6gcbw
220页深度神经网络训练归一化: 数学基础与理论、挑战
https://mp.weixin.qq.com/s/E7ajoDSxEGktqYuEfFo33A
220页深度神经网络基础、理论与挑战PPT
https://mp.weixin.qq.com/s/35vcaVsFPRTEWQ1ZP9y51Q
228页教程全面理解视觉定位技术
https://mp.weixin.qq.com/s/1MzoBW3e_crV1n-MMWjATg
308页教程介绍最新几何对象映射技术,functional maps
http://data8.org/
UCB的数据科学基础课程:The Foundations of Data Science
http://www.ds100.org/
UCB的数据科学高级课程:Principles and Techniques of Data Science
https://aws.amazon.com/cn/training/learning-paths/machine-learning/
亚马逊内部机器学习课程
https://mp.weixin.qq.com/s/mGM5nJJrWpSISWqXdlIDFg
计算机视觉入门教程系列—125页带你回顾CV发展脉络
https://mp.weixin.qq.com/s/o50c2cMjUSmR8Ea6v925_w
食物图像分析——55页PPT带你学习食物图像分析相关研究进展
您的打赏,是对我的鼓励