Kevin Duh’s Deep Learning Summary of NIPS 2012

For the ones who couldn’t attend NIPS 2012, Kevin Duh made an informative summary of NIPS 2012 Deep Learning related events, presentations and papers in his google+ page.

Deep Learning Representations

Yoshua Bengio’s Google tech talk about Deep Learning Representations at Google Montreal on 11/13/2012 is now on youtube Google Tech Talks Channel.

NIPS 2012 Deep Learning and Unsupervised Feature Learning Workshop

A deep learning workshop at NIPS 2012 was organized by Yoshua Bengio, James Bergstra and Quoc Le. The workshop demonstrated the great interest in deep learning by machine learning researchers: it got the largest format of room available, which was full, with hundreds of people, and for many talks people sitting on the floor or […]

First International Conference on Learning Representations(ICLR 2013)

ICLR 2013 in conjunction with AISTATS 2013, Scottsdale, Arizona, May 2nd-4th 2013

Submission deadline: January 15th 2013

One can submit a short-workshop like paper (not considered a publication) or a longer paper considered for publication in the ICLR proceedings or in a JMLR special issue. A novel reviewing and publication model is introduced, based on […]

An Interview on AI and Deep Learning with Yann Lecun and Peter Norvig

NPR’s Onpoint radio program interviewed Yann LeCun & Peter Norvig interviewed on NPR, on AI and deep learning.

[1] On Point: Artificial intelligence, Big Data, and deep learning, 29 November 2012,

Deep Learning Algorithms made front page on New York Times

A recent article written by John Markoff for New York Times raised the interest in deep learning algorithms[1] by the general audience. As a response to that news Gary Marcus wrote a critic about deep learning [2].

[1] New York Times, John Markoff, Scientists See Promise in Deep-Learning Programs, 23 November 2012

[2] The […]

Microsoft’s Richard Rashid demos deep learning for speech recognition in China

Chief Research Officer Rick Rashid demonstrates a speech recognition breakthrough via machine translation that converts his spoken English words into computer-generated Chinese language. The breakthrough is patterned after deep neural networks and significantly reduces errors in spoken as well as written translation [1].



University of Toronto Deep Learning Group won the Merck Drug Discovery Competition

A team led by George Dahl, a graduate student from University of Toronto won the Kaggle’s Merck Drug Discovery Challenge[1]. Machine Learning algorithm that they have used to won the challenge is using an ensemble of supervised learning algorithms. But the most important part of this algorithm is the deep neural network that they have […]

Google’s Large Scale Deep Learning Experiments

Google’s new large-scale learning experimentation using 16000 CPU cores and deep learning as part of google brain project had made a big success on Imagenet dataset. This success had a wide media coverage. Some pointers to the news:

Google official blog, 26 June 2012

NYT Front page on large scale neural network John Markoff, […]