CSAIL Event Calendar: Previous Series

Fast-learning neural models that maximize Shannon information storage

Speaker: David Staelin , EECS, MIT
Date: April 27 2010
Time: 4:15PM to 5:15PM
Location: 32-155
Host: Scott Aaronson, CSAIL, MIT

The human brain surpasses our finest computers using only ~30 watts, millisecond switching speeds, and unreliable neurons that individually signal via isolated voltage spikes sent roughly every second to perhaps 10,000 other neurons. We currently have no theoretical understanding of how this could work or what might constitute plausible performance bounds. Moreover, Blum and Rivest have shown that training even three canonical neurons in a classic reward-based fashion is arguably NP-complete, compounding our problem. Illustrative fundamental open theoretical questions include: 1) the proper definition of Shannon information in a neural context, 2) its practical upper bounds, and 3) identification of an explanatory neural model that permits these questions to be addressed with precision, even if biologically oversimplified.



A fast-learning neural model that can store perhaps 200 bytes will be presented along with suggestions of how such units might function collectively. The multi-faceted similarity between optimized model characteristics and those of cortical neurons will be summarized briefly, followed by suggestions of theoretical questions about neural spike processing that may now become addressable.

Joint work with K. T. Herring and C. H. Staelin

See other events that are part of Theory Colloquium 2009/2010

See other events happening in April 2010