James Anderson, Ph.D.

Teaching the Multiplication Tables to a Neural Network:
Flexibility vs. Accuracy

Jim Anderson's research concentrates on applications of neural networks to Cognitive Science. An appropriately designed network can do many pattern recognition functions in ways reminiscent of human performance. Neural networks have practical applications and can also serve as models for human behavior.

His group does research in several areas. Networks have been applied to models of human concept formation, to speech perception, and to models of low level vision, for example, the way local motion signals can be integrated to determine global object motion or the direction of self motion. A current project involves the study of elementary arithmetic, a problem that is surprisingly hard for both humans and neural networks. Study of elementary mathematics also raises questions about the way a neural network can be designed to perform effectively more general mathematical operations.

Recent work has considered how intermediate level structure in the nervous system might be configured, and how it might be detected in experimental data, as well as what kind of computations it might perform.

A model using a network of local networks is being studied, in light of data from both multiple unit recordings and functional MRI.

Selected Publications:

• Anderson, J.A. (1993), The BSB Model: A simple nonlinear autoassociative neural network, M. Hassoun (Ed.), Associative Neural Memories, New York, NY: Oxford U.
• Anderson, J.A. )1995), An Introduction to Neural Networks, Cambridge, MA: MIT Press.
• Anderson, J.A. Spoehr, K.T. and Bennett, D.J. (1994), A study in numerical perversity: Teaching Arithmetic to a neural network, Neural Networks for Knowledge Representation and Inference, D.S. Levine and M. Aparicio (Eds.), Hillsdale, NJ:Erlbaum.

Speaker Schedule  |  Reports from Previous Years
Top of Page | Life Sciences | Brandeis University