Yoshua Bengio on intelligent machines (17-02-2016)

scitechtalk tv

Yoshua Bengio on intelligent machines (17-02-2016)

http://www.iro.umontreal.ca/~bengioy/yoshua_en/

Yoshua Bengio
Full Professor
Department of Computer Science and Operations Research
Canada Research Chair in Statistical Learning Algorithms

Profile

Yoshua Bengio is Full Professor of the Department of Computer Science and Operations Research, head of the Montreal Institute for Learning Algorithms (MILA), CIFAR Program co-director of the CIFAR program on Learning in Machines and Brains, Canada Research Chair in Statistical Learning Algorithms. His main research ambition is to understand principles of learning that yield intelligence. He teaches a graduate course in Machine Learning (IFT6266) and supervises a large group of graduate students and post-docs. His research is widely cited (over 65000 citations found by Google Scholar in April 2017, with an H-index of 95).
Yoshua Bengio is currently action editor for the Journal of Machine Learning Research, associate editor for the Neural Computation journal, editor for Foundations and Trends in Machine Learning, and has been associate editor for the Machine Learning Journal and the IEEE Transactions on Neural Networks.

Yoshua Bengio was Program Chair for NIPS’2008 and General Chair for NIPS’2009 (NIPS is the flagship conference in the areas of learning algorithms and neural computation). Since 1999, he has been co-organizing the Learning Workshop with Yann Le Cun, with whom he has also created the International Conference on Representation Learning (ICLR). He has also organized or co-organized numerous other events, principally the deep learning workshops and symposiua at NIPS and ICML since 2007.

Recent Research Highlights

NEW CONFERENCE ON REPRESENTATION LEARNING: ICLR 2013
Almost full list of publications

Selected Recent Papers

Radically new approaches to deep unsupervised learning with joint training of all levels, avoiding marginalizing/MAP/MCMC over latent variables:
Exploiting the recent advances in understanding the probabilistic interpretation of auto-encoders in order to perform credit assignment without backprop and train deep generative models: How Auto-Encoders Could Provide Credit Assignment in Deep Networks via Target Propagation.
Deep Generative Stochastic Networks Trainable by Backprop, Yoshua Bengio, Eric Thibodeau-Laufer and Jason Yosinski, Université de Montréal, arXiv report 1306.1091, 2013 (also, an ICML’2014 paper).
Generalized Denoising Auto-Encoders as Generative Models, Yoshua Bengio, Li Yao, Guillaume Alain, and Pascal Vincent, Université de Montréal, arXiv report 1305.6663, 2013 (also, an NIPS’2013 paper
Python/Theano code for GSNs and the experiments in the above 2 papers.
Four challenges of deep learning, and ideas to attack them: scaling computation, optimization, inference & sampling, disentangling.
Deep Learning of Representations: Looking Forward, Yoshua Bengio, Université de Montréal, arXiv report 1305.0445, 2013
Figuring out what regularized auto-encoders are doing in terms of capturing the data generating distribution, and exploiting this to sample from them:
Recurrent nets are back!

A theory relating the evolution of culture and memes with local minima in deep neural networks

Deep Learning – an MIT Press book in preparation

Etc. Etc. Etc.

*******************************************************************

SciTechTalkTV is a radio- and TV Station on The Internet,
covering all the the wonderfull things in Science, Technology, Culture and topics of general interest and the unexpected links between them !

“On demand” (You can ask me to cover a topic on SciTechTalk), or as my personal initiative.

You can reach me at:
scitechtalktv AT gmail.com

Website: www.scitechtalk.org (under construction)

My objective: Share all relevant information with my audience concerning Science, Technology, Culture and Topics of General Interest (and all the unexpected links between them) and
cooperate with others videomakers !

Welcome to my channel:
https://www.youtube.com/channel/UCFxKBGTBFqgdIxplC7lftIg
I hope you revisit my channel !

If you like it, please like my youtube videos, so I can keep up the good work …. !

Better even: subscribe to my channel :
https://www.youtube.com/channel/UCUbS6L1YcQ1SHDldpXLfwTQ
for more and more interesting video’s
and live broadcasts in the future.

Thank you.

*******************************************************************

Source