Biomedical Engineering Reference
In-Depth Information
6
A NEUROMORPHIC SYSTEM
David P. M. Northmore
Department of Psychology, University of Delaware, Newark
John Moses
Biophysics Group, Los Alamos National Laboratory,
Los Alamos, New Mexico
John G. Elias
Department of Computer and Electrical Engineering,
University of Delaware, Newark
The essential functions of neurons can be emulated electronically on silicon chips. We
describe such a neuron analogue, or neuromorph, that is compact and low power, with
sufficient flexibility that it could perform as a general-purpose unit in networks for con-
trolling robots or for use as implantable neural prostheses. We illustrate some possible
applications by a dynamical network that recognizes spatiotemporal patterns and by a
network that uses a biologically inspired learning rule to develop sensory-guided behav-
ior in a moving robot. Finally, design requirements for neuromorphic systems are dis-
cussed.
1.
INTRODUCTION : ARTIFICIAL NERVOUS SYSTEMS
In the quest for alternative forms of computing, especially computing that
generates useful behavior in the real world, one naturally looks to biology for
inspiration. While brains are economical in size and energy consumption, they
depend for their computing power and speed on very large numbers of process-
Address correspondence to: John G. Elias, Department of Computer and Electrical Engineering,
University of Delaware, 105 Evans Hall, Newark, DE 19716 (elias@ee.udel.edu).
811
 
Search WWH ::




Custom Search