Graduate Summer School: Deep Learning, Feature Learning

Organizing Committee | Scientific Overview | Speaker List

Application/Registration | Contact Us

Yoshua Bengio (University of Montreal, Canadian Institute for Advanced Research)
Geoffrey Hinton (University of Toronto, Canadian Institute for Advanced Research)
Yann LeCun (New York University, Canadian Institute for Advanced Research)
Andrew Ng (Stanford University, Canadian Institute for Advanced Research)
Stanley Osher (University of California, Los Angeles (UCLA))

Back to Top

One of the challenges for machine learning, AI, and computational neuroscience is the problem of learning representations of the perceptual world. This summer school will review recent developments in feature learning and learning representations, with a particular emphasis on "deep learning" methods, which can learn multi-layer hierarchies of representations.

Topics will include unsupervised learning methods such as stacked restricted Boltzmann machines, sparse coding, denoising auto-encoders, and methods for learning over-complete representations; supervised methods for deep architectures, metric learning criteria for vector-space embeddings; deep convolutional architectures and their applications to images, video, audio, and text; compositional hierarchies and latent-variable models.

Mathematical issues will be addressed, particularly how to characterize the low-dimensional structure of natural data in high-dimensional spaces; training density models with intractable partition functions; the geometry of non-convex and ill-conditioned loss functions for deep learning; efficient optimization methods for inference and deep learning; the representational efficiency of deep architectures, and the advantages of high-dimensional and over-complete representations.

The Canadian Institute for Advanced Research (CIFAR) is cosponsoring the program. Ten students associated with CIFAR’s Neural Computation and Adaptive Perception (NCAP) Program will participate with CIFAR support.

Back to Top

Back to Top

Application

An application form is available at:

You must apply and be accepted in order to attend the workshop. The application is also for people requesting financial support. We urge you to apply as early as possible. Applications received by Thursday, March 22, 2012 will receive fullest consideration. Letters of reference may be sent to the address or email address below. Successful applicants will be notified as soon as funding decisions are made.

We have funding especially to support the attendance of recent PhD's, graduate students, and researchers in the early stages of their career; however, mathematicians and scientists at all levels who are interested in this area are encouraged to apply for funding. Encouraging the careers of women and minority mathematicians and scientists is an important component of IPAM's mission and we welcome their applications.

Back to Top

Contact Us:

Institute for Pure and Applied Mathematics (IPAM)
Attn: GSS2012
460 Portola Plaza
Los Angeles CA 90095-7121
Phone: 310 825-4755
Fax: 310 825-4756
Email:
Website: http://www.ipam.ucla.edu/programs/gss2012/

Back to Top