Keywords

neural networks, recurrently-connected, time delays, time constants

Abstract

Recurrently-connected spiking neural networks are difficult to use and understand because of the complex nonlinear dynamics of the system. Through empirical studies of spiking networks, we deduce several principles which are critical to success. Network parameters such as synaptic time delays and time constants and the connection probabilities can be adjusted to have a significant impact on accuracy. We show how to adjust these parameters to fit the type of problem.

Original Publication Citation

Eric Goodman and Dan Ventura, "Effectively Using Recurrently Connected Spiking Neural Networks", Proceedings of the International Joint Conference on Neural Networks, pp. 1542-1547, July 25.

Document Type

Peer-Reviewed Article

Publication Date

2005-07-01

Permanent URL

http://hdl.lib.byu.edu/1877/2522

Publisher

IEEE

Language

English

College

Physical and Mathematical Sciences

Department

Computer Science

Share

COinS