$500,000 NSF Grant To Discover The Learning Algorithm Of The Brain Received By NYU's Courant Institute

Main Category: IT / Internet / E-mail
Also Included In: Neurology / Neuroscience;  Eye Health / Blindness
Article Date: 06 Oct 2008 - 0:00 PDT

email to a friend   printer friendly   opinions  

New York University's Courant Institute of Mathematical Sciences and its institutional partners - Stanford University, MIT, and the University of California, Berkeley - have each received a $500,000 grant from the National Science Foundation to study the "learning algorithm of the brain." The four-year, $2 million project seeks to develop new computational models of how the visual system learns to recognize objects.

"How can our visual system learn to recognize object categories, such as dog, airplane, or chair by merely being shown a small number of examples of each category?" said NYU's Yann LeCun, a professor of computer science at the Courant Institute. "This project will enhance our understanding of this process by drawing on the recent progress in a new class of machine learning methods called 'deep belief networks,' and through new experimental methods to study the visual cortex."

The project's researchers hope to uncover new mechanisms that could explain the learning process in neural circuits. These experiments, they contend, will attempt to discover what role the feedback connections in the visual cortex play during learning. Results from psychophysics, neuroscience, and computational modeling show that the rapid recognition of everyday objects can be explained by a viewing the visual cortex as a multi-layer, feed-forward system in which the neural activity propagates from the eye to the higher brain areas, with little feedback from the higher layers to the lower layers. Yet, there are as many feedback connections as feed-forward connections in the visual cortex. The researchers will seek to understand their role.

"Learning algorithms for deep belief network could constitute a good model for how the visual cortex learns because they can be applied to multi-layer architectures similar to the visual cortex, and because feedback connections play a crucial role in the learning process in these models," LeCun noted. "A set of experiments will establish whether feedback connections in the brain play a similar role in learning."

The grants, which come out of NSF's Office of Emerging Frontiers in Research and Innovation (EFRI), support interdisciplinary teams will pursue transformative, fundamental research in two areas: understanding the brain and how its abilities may be used through cognitive optimization and prediction; and developing ways to make complex, interdependent infrastructure systems more resilient and sustainable.

###

Source: James Devitt
New York University

• Additional
• References
• Citations