Deep Learning Tutorials

转发自：http://deeplearning.net/reading-list/tutorials/

Survey Papers onDeep Learning

Yoshua Bengio, LearningDeep Architectures for AI,Foundations and Trends in Machine Learning, 2(1), pp.1-127, 2009.

Yoshua Bengio, Aaron Courville, Pascal Vincent, RepresentationLearning: A Review and New Perspectives, Arxiv, 2012.

Deep Learning CodeTutorials

The Deep LearningTutorials are awalk-through with code for several important Deep Architectures (in progress;teaching material for Yoshua Bengio’s IFT6266 course).

UnsupervisedFeature and Deep Learning

Stanford’s Unsupervised Feature and Deep Learning tutorials has wiki pages and matlab code examples for severalbasic concepts and algorithms used for unsupervised feature learning and deeplearning.

Videos

• Deep Learning Representations

Yoshua Bengio’s Google tech talk on Deep LearningRepresentations at Google Montreal (Google Montreal, 11/13/2012)

• Deep Learning with Multiplicative Interactions

Geoffrey Hinton’s talk at the Redwood Center for Theoretical Neuroscience (UCBerkeley, March 2010).

• Recent developments on Deep Learning

Geoffrey Hinton’s GoogleTechTalk, March 2010.

• Learning Deep Hierarchies of Representations 

A generalpresentation done byYoshua Bengio in September 2009, also at Google.

• A New Generation of Neural Networks 

Geoffrey Hinton’s December2007 Google TechTalk.

• Deep Belief Networks

Geoffrey Hinton’s 2007 NIPS Tutorial [updated 2009] onDeep Belief Networks 3hour video , ppt, pdf, readings

• Training deep networks efficiently

Geoffrey Hinton’s talk at Google about dropout and “Brain, Sex and MachineLearning”.

• Deep Learning and NLP

 Yoshua Bengio and Richard Socher’s talk, “Deep Learningfor NLP(without magic)” at ACL 2012.

• Tutorial on Learning Deep Architectures

Yoshua Bengio and Yann LeCun’s presentation at “ICMLWorkshop on Learning Feature Hiearchies” on June 18th 2009.

Energy-basedLearning

[LeCunet al 2006]. A Tutorial on Energy-Based Learning, inBakir et al. (eds) “Predicting Structured Outputs”, MIT Press 2006: a 60-pagetutorial on energy-based learning, with an emphasis on structured-outputmodels. The tutorial includes an annotated bibliography of discriminativelearning, with a simple view of CRF, maximum-margin Markov nets, and graphtransformer networks.

A 2006 Tutorial an Energy-Based Learning given at the 2006 CIAR Summer School: Neural Computation &Adaptive Perception.[Energy-BasedLearning: Slidesin DjVu (5.2MB), Slidesin PDF (18.2MB)] [DeepLearning for Generic Object Recognition:Slidesin DjVu (3.8MB), Slidesin PDF (11.6MB)]

ECCV 2010 Tutorial

Featurelearning for Image Classification (byKai Yu and Andrew Ng): introducing a paradigm of feature learning fromunlabeled images, with an emphasis on applications to supervised imageclassification.

NIPS 2010 Workshop

DeepLearning and Unsupervised Feature Learning: basic concepts about unsupervised feature learning anddeep learning methods with links to papers and code.

Summer Schools

GraduateSummer School: Deep Learning, Feature Learning: IPAM summer school about deep learning.

 OnlineCourses

Geoffrey Hinton’s OnlineNeural networks Course onCoursera.