CAMBRIDGE, Massachusetts—March 25, 2004—The McGovern Institute at MIT, a leading research and teaching institute committed to advancing understanding of the human mind and communications, announced today that Tomaso Poggio, one of its Principal Investigators has co-authored a paper being published in Nature Magazine that outlines a new paradigm that could lead to building smarter machines, predicting future occurrences and understanding how people learn.

"General Conditions for Predictivity in Learning Theory" offers an advanced mathematical theorem, based on the recognition that learning is more than memory; rather it is the ability to take stored information, stabilize and generalize it, and apply it to novel situations accurately.

While extremely complex, the implications of this work could lead to such things as:

• Intelligent machines that can actually learn instead of being painfully programmed;
• Advanced applications for medical diagnoses;
• Programs that could power numerous advances in technology, including searching the Web, visual inspection, smart robots, language learning, etc.;
• An understanding of the conditions in scientific research that lead to "scientific" theories;
• More accurate predictions of future financial markets;
• Better understanding of how the human brain learns complex tasks such as in motor control, vision and language learning.

If you would like to discuss Dr. Poggio's findings and the paper, co-authored with Ryan Rifkin, Sayan Mukherjee and Partha Niyogi, please contact Derek Beckwith or Lyn Chamberlin at 978-443-0400.

About the McGovern Institute at MIT

The McGovern Institute at MIT is a research and teaching institute committed to advancing human understanding and communications. The goal of the McGovern Institute is to investigate and ultimately understand the biological basis of all higher brain function in humans. The McGovern Institute conducts integrated research in neuroscience, genetic and cellular neurobiology, cognitive science, computation, and related areas.

By determining how the brain works, from the level of gene expression in individual neurons to the interrelationships between complex neural networks, the McGovern Institute's efforts work to improve human health, discover the basis of learning and recognition, and enhance education and communication. The McGovern Institute contributes to the most basic knowledge of the fundamental mysteries of human awareness, decisions, and actions.

For additional information, please go to http://web.mit.edu/mcgovern

About Tomaso Poggio

Tomaso Poggio is a computational neuroscientist whose recent work focuses on the processes by which the brain learns to recognize and categorize visual objects. His work is important not only towards understanding higher brain function, but also for the mathematical and computer applications of statistical learning.

Poggio is Eugene McDermott Professor in the Department of Brain and Cognitive Sciences and at the Artificial Intelligence Laboratory. He is also Co-Director of the Center for Biological and Computational Learning and was appointed Investigator immediately after the establishment of the McGovern Institute in 2000. He joined the MIT faculty in 1981, after ten years at the Max Planck Institute for Biology and Cybernetics in Tubingen, Germany. He received a Ph.D. in 1970 from the University of Genoa. Poggio is a Foreign Member of the Italian Academy of Sciences and a Fellow of the American Academy of Arts and Sciences.

Contact:
Derek Beckwith
skyemedia, inc.
978-443-0400
derek@skyepr.com

###