AIC Seminar Series

Humans can recognize objects despite the drastically different images that they project on our retina under different situations. This is known as the invariance property. How this invariance is achieved is still a mystery for computer vision and neuroscience researchers. In this talk Dileep George will review the past approaches for solving this problem and describe a new way of thinking about the Invaraince Problem under the Memory-Prediction formalism described in "On Intelligence". He will describe how Invariance can be obtained automatically as a result of learning to predict the future. The talk will include a probabilistic formulation of the Memory-Prediction framework and a demonstration of results achieved so far on a space of binary line-drawing images.

Dileep George is a Graduate Research Fellow at the Redwood Neuroscience Institute and a PhD student in Electrical Engineering at Stanford University. His current research is on building statistical models of memory and prediction with a focus on biological vision. He received a B.Tech in Electrical Engineering from Indian Institute of Technology - Bombay and an MS in Electrical Engineering from Stanford University. He spent several years in the industry and designed baseband receiver algorithms for 3rd generation wireless devices before getting interested in neuroscience.

Please arrive at least 10 minutes early in order to sign in and be escorted to the conference room. SRI is located at 333 Ravenswood Avenue in Menlo Park. Visitors may park in the visitors lot in front of Building E, and should follow the instructions by the lobby phone to be escorted to the meeting room. Detailed directions to SRI, as well as maps, are available from the Visiting AIC web page.

©2013 SRI International 333 Ravenswood Avenue, Menlo Park, CA 94025-3493
SRI International is an independent, nonprofit corporation. Privacy policy