网络上有大量视频课程和教程,其中许多都是免费的。也有一些很好的付费课程,但本文主要提供免费内容的推荐。有相当多的大学课程都提供在线课程材料,但没有视频。以下课程可以足够你忙上几个月了:

 

Coursera — 机器学习(Machine Learning) 

授课:Andrew Ng

https://www.coursera.org/learn/machine-learning#syllabus

 

Coursera — 机器学习神经网络(Neural Networks for Machine Learning)

授课:Geoffrey Hinton

https://www.coursera.org/learn/neural-networks

 

Udacity — 机器学习导论(Intro to Machine Learning)

授课:Sebastian Thrun

https://classroom.udacity.com/courses/ud120

 

Udacity — 机器学习(Machine Learning)

授课:Georgia Tech

https://www.udacity.com/course/machine-learning--ud262

 

Udacity — 深度学习(Deep Learning)

授课:Vincent Vanhoucke

https://www.udacity.com/course/deep-learning--ud730

 

机器学习(Machine Learning)

授课:mathematicalmonk

https://www.youtube.com/playlist?list=PLD0F06AA0D2E8FFBA

 

给程序员的机器学习实践课程(Practical Deep Learning For Coders)

授课:Jeremy Howard & Rachel Thomas

http://course.fast.ai/start.html

 

Stanford CS231n —面向视觉识别的卷积神经网络( Convolutional Neural Networks for Visual Recognition) (Winter 2016)

授课:李飞飞、Justin Johnson & Serena Yeung 

http://cs231n.stanford.edu/

 

Stanford CS224n — 深度学习与自然语言处理(Natural Language Processing with Deep Learning)(Winter 2017) 

授课:Chris Manning & Richard Socher 

http://web.stanford.edu/class/cs224n/

 

哈佛深度NLP课程(Oxford Deep NLP 2017 )

授课:Phil Blunsom et al.

https://github.com/oxford-cs-deepnlp-2017/lectures

 

强化学习(Reinforcement Learning)

授课:David Silver

http://www.cs.ucl.ac.uk/staff/d.silver/web/Teaching.html

 

Python实践机器学习教程(Practical Machine Learning Tutorial with Python)

授课:sentdex

https://www.youtube.com/watch?list=PLQVvvaa0QuDfKTOs3Keq_kaG2P55YRn5v&v=OGxgnH8y2NM

 

 

书籍             

 

有很多书籍,涵盖机器学习,深度学习和NLP的一些方面。在本节中,我将聚焦于可以直接从网页访问或下载的免费书籍。

 

机器学习:

 

理解机器学习,从理论到算法(Understanding Machine Learning From Theory to Algorithms,http://101.96.8.164/www.cs.huji.ac.il/~shais/UnderstandingMachineLearning/understanding-machine-learning-theory-algorithms.pdf)

Machine Learning Yearning,作者:Andrew Ngwww.mlyearning.org/)

机器学习课程(A Course in Machine Learning,http://ciml.info)

机器学习(Machine Learning,https://www.intechopen.com/books/machine_learning)

神经网络与机器学习(Neural Networks and Deep Learning,neuralnetworksanddeeplearning.com/)

深度学习图书(Deep Learning Book,www.deeplearningbook.org/)

强化学习导论(Reinforcement Learning: An Introduction,incompleteideas.net/sutton/book/the-book-2nd.html)

强化学习(Reinforcement Learning,https://www.intechopen.com/books/reinforcement_learning)

 

NLP

 

对话与语言处理(第三版)(Speech and Language Processing (3rd ed. draft),https://web.stanford.edu/~jurafsky/slp3/)

Python自然语言处理(Natural Language Processing with Python,www.nltk.org/book/)

信息检索概论(An Introduction to Information Retrieval,https://nlp.stanford.edu/IR-book/html/htmledition/irbook.html)

 

数学

 

统计思维概论(Introduction to Statistical Thought,people.math.umass.edu/~lavine/Book/book.pdf)

贝叶斯统计学概论 (Introduction to Bayesian Statistics,https://www.stat.auckland.ac.nz/~brewer/stats331.pdf)

概率论概论(Introduction to Probability,https://www.dartmouth.edu/~chance/teaching_aids/books_articles/probability_book/amsbook.mac.pdf)

统计思维:面向Python程序员的概率论与统计学(Think Stats: Probability and Statistics for Python programmers,greenteapress.com/wp/think-stats-2e/)

概率论与统计学实践指南(The Probability and Statistics Cookbook,statistics.zone/)

线性代数(Linear Algebra,joshua.smcvt.edu/linearalgebra/book.pdf)

线性代数错误集锦(Linear Algebra Done Wrong,www.math.brown.edu/~treil/papers/LADW/book.pdf)

线性代数(理论与实践)(Linear Algebra, Theory And Applications,https://math.byu.edu/~klkuttle/Linearalgebra.pdf)

面向计算机科学的数学(Mathematics for Computer Science,https://courses.csail.mit.edu/6.042/spring17/mcs.pdf)

微积分学(Calculus,https://ocw.mit.edu/ans7870/resources/Strang/Edited/Calculus/Calculus.pdf)

计算机科学与统计学学生用的微积分学(Calculus I for Computer Science and Statistics Students,www.math.lmu.de/~philip/publications/lectureNotes/calc1_forInfAndStatStudents.pdf)

 

image.png