ICLR 2014 Videos are available online

International Conference on Learning Representations (ICLR 2014) held between 14th of April and 16th of April in Banff with great interest from the deep learning community. The videos of talks are made available by the organizers at a Youtube channel[1].

[1]Youtube channel for ICLR 2014, https://www.youtube.com/playlist?list=PLhiWXaTdsWB-3O19E0PSR0r9OseIylUM8

An Article about History of Deep Learning

Wired has just published a new article about brief history of deep learning and the role of Hinton on development of the deep learning field. The article also mentions about CIFAR and the contribution of its member to deep learning:


Google’s new Deep Learning Algorithm Transcribes House Numbers

During his summer internship, Ian Goodfellow (currently a PhD student at UdeM Lisa Lab) and his collaborators from Google, Yaroslav Bulatov, Julian Ibarz, Sacha Arnoud, Vinay Shet, submitted a paper to ICLR 2014 that proposes a deep learning method which successfully transcribes the house numbers from Google Streetview images. This work took wide coverage in […]

Facebook Hires Yann Lecun

Facebook decided to hire prominent NYU professor Yann LeCun as the new director of their AI lab. Yann LeCun will still be a part time professor at NYU at newly established Data Science Institute. Another NYU professor Rob Fergus will also join the Facebook AI team. Mark Zuckerberg officially announced that they hired Yann LeCun […]

Yahoo Acquires Startup LookFlow To Work On Flickr And ‘Deep Learning’

LookFlow, a startup that describes itself as “an entirely new way to explore images you love,” just announced that it has been acquired by Yahoo and will be joining the Flickr team[1,2,3]. The company is cofounded by Bobby Jaros and Simon Osindero. Their company was utilizing deep learning techniques for image recognition problems[1,2].

News sources:


Deep Learning Successes Obtained by IDSIA

IDSIA is one of the largest and oldest lab that focuses on deep learning. Their machine learning team is being led by Jürgen Schmidhuber. In the last 5 years, they had several successes on different machine learning competitions. Here are some of their recent competitive achievements in competitions and challenges:

22 Sept 2013: Deep neural […]

A new machine learning startup uses Maxout and Stochastic Pooling in their Pipeline

According to a recently published gigaOM article, a Denver based startup (AlchemyAPI) started to use Maxout [1] and Stochastic Pooling [2] in their object recognition pipeline. Using those deep learning techniques, they claim to deliver Google-level machine learning services.

[1] Goodfellow, I. J., Warde-Farley, D., Mirza, M., Courville, A., & Bengio, Y. , Proceedings of […]

A paper on Pylearn2 is released

A paper about Pylearn2 and its architecture has been published on arXiv. It can be accessed via the following link: http://arxiv.org/pdf/1308.4214v1.pdf . If you use Pylearn2 in research publications, please cite this paper. An example bibtex entry is:

@ARTICLE{pylearn2_arxiv_2013, title={Pylearn2: a machine learning research library}, author={Ian J. Goodfellow and David Warde-Farley and Pascal Lamblin and […]

What is deep learning and why should we care about it?

Another article about deep learning has been published, this time at Forbes. The article is discussing why business should care about deep learning:


Yoshua Bengio’s talk at MSR about Deep Learning of Representations and GSNs

Yoshua Bengio gave a recent presentation on “Deep Learning of Representation” and Generative Stochastic Networks (GSNs) at MSR and AAAI 2013. Slides of the talk can be accessed from this link.