Keywords

relaxation network, probabilistic connections, input persistence, activation function

Abstract

This paper reports results from studying the behavior of Hopfield-type networks with probabilistic connections. As the probabilities decrease, network performance degrades. In order to compensate, two network modifications - input persistence and a new activation function - are suggested, and empirical results indicate that the modifications significantly improve network performance.

Original Publication Citation

Dan Ventura, "Probabilistic Connections in Relaxation Networks", Proceedings of the International Joint Conference on Neural Networks, pp.934-938, May 22.

Document Type

Peer-Reviewed Article

Publication Date

2002-05-01

Permanent URL

http://hdl.lib.byu.edu/1877/2532

Publisher

IEEE

Language

English

College

Physical and Mathematical Sciences

Department

Computer Science

Share

COinS