Learning resources for machine learning and computer vision

Machine Learning (machines learning, abbreviated ML) and computer vision (computer vision, or CV) are fascinating, very cool, challenging and a wide area to cover. This article has organized the learning resources related to machine learning and computer vision in order to help many people who, like me, want to understand the principles behind "intelligence" and learn the most cutting-edge technologies and knowledge in the most efficient way.

wikipedia.org, History, field overview, resource Links:

Machine learning, introduced the problem of ML, common algorithms, applications, software, etc., the right side lists the subdivision entries;

List of machine learning Concepts,category:machine Learning, listing more ml related concepts and articles;

Computer vision, the same, introduced the CV processing problems, common methods, applications, etc., the bottom of the list of sub-items;

List of computer vision Topics,category:computer Vision, which lists more CV-related items.

University courses, online tutorials :

Stanford about ML and CV computer courses (sorted by recommendation): cs229Machine Learning, cs229tStatistical learning theory, cs231nconvolutional neural Networks for Visual recognition,cs231acomputer Vision:from 3D recontruct to recognition,cs231bThe cutting Edge of computer Vision,cs221Artificial Intelligence:principles & Techniques,cs131computer vision:foundations and Applications,cs369lA Theoretical perspective on machine learning,cs205aMathematical Methods for Robotics, Vision & Graph,cs231mMobile Computer Vision, most of these courses can be downloaded PPT, more courses please seeCourses | Stanford Computer Science, an ML course in Open classMachine learning,Unsupervised Feature learning and deep learning, Coursera ml course: machine learning, and Stanford online tutorialsDeep learning Tuorial;

More university courses can be searched for by "machine learning course" or "Computer Vision course", which is a domestic image of Google, so there is no need for Fanqiang.

Monographs, Books :

ML:

Statistical learning methods, Hangyuan Li, 2012;

Deep learning:methods and applications, Li Deng and Dong Yu, 2014;

Introduction to Machine Learning (3rd ed.), Ethem Alpaydin, 2014;

Machine Learning:an Algorithmic Perspective (2nd ed.), Stephen Marsland, 2015;

Deep Learning, an online book;

Neural Networks and Learning Machines (3rd ed.), Simon O. Haykin, 2008, with Chinese translation: Neural Network and machine learning;

Pattern recognition and machine learning, Christopher Bishop, 2006; There is a Chinese translation: mode recognition and computer learning;

CV:

Concise computer Vision:an Introduction into theory and algorithms, Klette, Reinhard, 2014;

Computer vision:algorithms and applications, Szeliski, Richard, 2011;

Multiple View Geometry in Computer Vision (2nd ed.), Richard Hartley and Andrew Zisserman, 2004;

An invitation to- Vision:from Images to geometric Models, Yi Ma, Stefano Soatto, Jana Kosecka, S. Shankar Sastry, 2004;

Robot Vision, Berthold K. Horn, 1986, with Chinese translation: Machine vision;

Image processing, analysis, and Machines Vision (3rd ed.), Milan Sonka, Vaclav Hlavac, Roger Boyle, 2007; Chinese translation: Image processing, analytics and machine vision ；

Recommend a very good search for English ebook website: Library Genesis.

Academic Papers :

Top journals in ML, CV: TPAMI,IJCV, top academic conferences: CVPR,ICML, ICCV,NIPS,ECCV,ACCV, etc.;

Cvpapers has done a good job in the field of CV academic papers;

ImageNet Annual Image Recognition competition is very representative of the highest level of CV;

arxiv.org, many of the latest papers were first published here;

Of course, Google Scholar is recommended, this is a mirror site.

Learning website :

Deeplearning.net: A very good machine learning site, with a dataset, software, reading list connection;

Visionbib.com: The CV resources of the academic Daniel's reorganization;

Cvonline has a very comprehensive resource link.

programs, Libraries :

OpenCV: A C + + visual library, widely used;

Torch, Theano: Two very powerful Python machine learning libraries that support cuda graphics acceleration;

Caffe: Deep learning libraries used by many researchers;

R language: An environment that facilitates the development of machine learning programs;

More libraries, here's a good summary.

Learning resources for machine learning and computer vision