Biological Cybernetics

, Volume 46, Issue 1, pp 27–39

Dynamic connections in neural networks

  • Jerome A. Feldman
Article

DOI: 10.1007/BF00335349

Cite this article as:
Feldman, J.A. Biol. Cybern. (1982) 46: 27. doi:10.1007/BF00335349

Abstract

Massively parallel (neural-like) networks are receiving increasing attention as a mechanism for expressing information processing models. By exploiting powerful primitive units and stability-preserving construction rules, various workers have been able to construct and test quite complex models, particularly in vision research. But all of the detailed technical work was concerned with the structure and behavior offixed networks. The purpose of this paper is to extend the methodology to cover several aspects of change and memory.

Copyright information

© Springer-Verlag 1982

Authors and Affiliations

  • Jerome A. Feldman
    • 1
  1. 1.Computer Science DepartmentUniversity of RochesterRochesterUSA