Share Email Print

Proceedings Paper

Spatiotemporal neurons and local learning rules enabling massively parallel neurocomputers
Author(s): Arno J. Klaassen
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this paper we present a way to provide neural networks, at the same time, both with a natural notion of time and with locality and modularity in computation. By doing so we ease massively parallel implementations. At the neuron level we introduce pulse code cable neurons, a neuron model with spatio-temporal information processing capabilities and much reduced communication bandwidth; its constituting parts either are branched, one-dimensional electrically equivalent cables of neuronal membrane in which all information processing takes place locally, or 1 bit delayed interconnections that unidirectionally connect one membrane to another. At the network level we argue that the theory of Neuronal Group Selection is an apt candidate for providing modularity by means of its `group-forming' local learning rules. We show that, taking dimensions from biological reality, the overall computation time scales with the spatial and temporal accuracy with which we model a membrane, rather than with the number of neurons or synapses. Routing the interconnections remains a problem, but with current technology real-time simulation of some millions of interconnections seems readily feasible.

Paper Details

Date Published: 1 July 1992
PDF: 12 pages
Proc. SPIE 1710, Science of Artificial Neural Networks, (1 July 1992); doi: 10.1117/12.140140
Show Author Affiliations
Arno J. Klaassen, Delft Univ. of Technology (Netherlands)

Published in SPIE Proceedings Vol. 1710:
Science of Artificial Neural Networks
Dennis W. Ruck, Editor(s)

© SPIE. Terms of Use
Back to Top