Biologically Inspired Computation and Learning Algorithms
Daniel D. Lee
Bell Laboratories, Lucent Technologies
Why is it that if computers have gotten so much faster and cheaper, they have no t become any better at understanding what we want them to do? Some of the tasks we take for granted such as vision and language are still too difficult for the latest supercomputers to handle. To us, a picture may be worth a thousand words, but to a machine it's just a seemingly random jumble of numbers. How can we prog ram computers to process this kind of information? Algorithms that mimic the way our brains compute and learn may be the answer. I will talk about some prototy pical systems that I have built with embedded processors, sensors, and wireless networking technologies. We'll see examples of how biologically inspired computa tion and learning can be applied to controlling these systems. Daniel Lee received his B.A. in physics from Harvard College in 1990 and a Ph. D. in condensed matter physics from MIT in 1995. He is now a member of the techn ical staff in the Biological Computation department at Bell Labs, trying to unde rstand the general principles that biological systems use to process and organiz e information. He works on applying that knowledge to building better artificial systems for vision, speech, language, and data communications. Besides playing w ith his robots, he enjoys ice hockey, scuba diving, and automating the house for his wife and their cat.
This page is maintained by InYoung Kim (firstname.lastname@example.org).
Last update: November 15, 2000