Some tutorials for deep learning

Transferred from: http://baojie.org/blog/2013/01/27/deep-learning-tutorials/

A few good deep learning tutorials, with basic videos and speeches. Two articles and a comic book are attached. There are some additions later.

Jeff Dean @ Stanford

Http://i.stanford.edu/infoseminar/dean.pdf

An introductory introduction to what DL can do, primarily in the three directions that Google uses for speech recognition, image processing, and natural language processing. "Spanner and Deep Learning" (2013-01-19)

Hinton 2009

A tutorial on Deep learning

Slideshttp://videolectures.net/site/normal_dl/tag=52790/jul09_hinton_deeplearn.pdf

Video http://videolectures.net/jul09_hinton_deeplearn/(3 hours)

From the background of the neural network to analyze the DL, why should have a DL said very clearly. The basic model structure of the DL is also clearly stated. Very recommended

More Hinton Tutorials http://www.cs.toronto.edu/~hinton/nntut.html

Stanford's Deep Learning Open Class (2012)

Samy Bengio, Tom Dean and Andrew Ng

Http://openclassroom.stanford.edu/MainFolder/CoursePage.php?course=DeepLearning

The language of instruction is MATLAB.

Lessons for 2011 years cs294a/cs294w Deep learning and unsupervised Feature learning

• UFLDL Tutorial wiki:unsupervised Feature Learning and deep learning Tutorial not long, easy to understand

More Stanford jobs: Deep learning in Natural Language processing

NIPS TutorialDeep Learning-Natural Language processing, tutorial by Ronan Collobert (Senna author)

• Http://ronan.collobert.com/pub/matos/2009_tutorial_nips.pdf
• Video http://videolectures.net/nips09_collobert_weston_dlnl/

This introduces the application of DL in three directions: tagging (parsing), semantic search, concept labeling

Ronan Collobert's Senna is a C deep learning implementation with only more than 2000 lines of code

ACL Tutorial

Deep Learning for NLP (without Magic)

Http://www.socher.org/index.php/DeepLearningTutorial/DeepLearningTutorial by Richard Socher, Yoshua Bengio and Chris Manning pdf:http://nlp.stanford.edu/~socherr/socherbengiomanning-deeplearning-acl2012-20120707-nomargin.pdf

Video:http://www.youtube.com/watch?v=if5tgegrctq&list=pl4617d0e28a5781b0

Kai Yu ' s Tutorialhttp://vipl.ict.ac.cn/news/academic-report-tutorial-deep-learning-dr-kai-yu on November 26, 2012Title: "A Tutorial on Deep learning"   abstract: in the past of years, tremendous progress has been made In building effective classification models. Despite the success, we have to realize that, in major AI challenges, the key bottleneck are not the quality of classifiers But that's features. Since 2006, learning high-level features using deep architectures have become a big wave of new learning paradigms. In recent years, performance breakthrough is reported in both image and speech recognition tasks, indicating deep Lea Rning is not something ignorable. In this talk, I'll walk through the recent works and key building blocks, e.g, sparse coding, RBMs, auto-encoders, etc. and list the major topics, including modeling and computational issues. In the end, I'll discuss what might is interesting topics for future Research.  bio OF Dr. Kai yu:  Kaiyu, vice director of Baidu Technology, head of multimedia, is responsible for the research and development of Internet and mobile applications in the fields of voice, image and audio. Prior to joining Baidu, Dr. Kaiyu was head of the media Analytics Department at the NEC Institute in the United States (Department Head), leading the team in product technology development in machine learning, image recognition, multimedia retrieval, video surveillance, and data mining and human-computer interaction. He previously worked at Siemens as senior scientist. "CS121: Introduction to Artificial Intelligence", a guest speaker at Stanford University's computer department in 2011. He has published more than 70 papers in conferences and magazines such as Nips, ICML, CVPR, ICCV, Eccv,sigir, Sigkdd,tpami,tkde, h-index=28, and has served as an international conference on machine Learning ICML10, ICML11, NIPS11, NIPS12 's Area Chair. In 2012, he was named Zhongguancun High-end leader and high-level overseas talents of Beijing Hai Ju plan.   

Slides Link:http://pan.baidu.com/share/link?shareid=136269&uk=2267174042[1]

Video Link: Kaiyu_report.mp4 (519.2 MB)

Theano Deep Learning Tutorial

This is the actual combat, how to use Python to achieve deep learning

http://deeplearning.net/tutorial/

Code https://github.com/lisa-lab/DeepLearningTutorials Survey Papers

A lot, but beginners look at these two should be enough

Yoshua Bengio, Aaron Courville, Pascal Vincent. (representation) Learning:a Review and New perspectives

Yoshua Bengio (2009). Learning deep architectures for AI.

More

• Itamar Arel, Derek c. Rose, and Thomas p. Karnowski. Learning–a New Frontier in Artificial Intelligence study This is no formula, not long, is a general introduction
• Some important articles up to 2009 Http://www.iro.umontreal.ca/~lisa/twiki/bin/view.cgi/Public/ReadingOnDeepNetworks

Finally, a comic.

Deep learning although good, also must bear in mind its limitation

Some tutorials for deep learning