Title :
Evolving synaptic connections for a silicon neuromorph
Author :
Northmore, David P M ; Elias, John G.
Author_Institution :
Neurosci. Program & Electr. Eng., Delaware Univ., Newark, DE, USA
Abstract :
Our VLSI neuromorphs possess extensive dendritic trees with hundreds of excitatory and inhibitory synaptic sites. Useful signal processing can be achieved by evolving the appropriate connections to the synapses using genetic algorithms. In order to reduce the very large solution space, schemes for specifying connections have been borrowed from neural development. Results show the evolution of connections to a single neuromorph for the discrimination of temporal and spatio-temporal patterns
Keywords :
VLSI; genetic algorithms; neural chips; pattern recognition; signal processing; temporal reasoning; VLSI neuromorphs; dendritic trees; excitatory synaptic sites; genetic algorithms; inhibitory synaptic sites; neural development; signal processing; solution space; spatiotemporal patterns; synaptic connections evolution; temporal pattern discrimination; Biomedical signal processing; Biomembranes; Circuits; Immune system; Neurons; Neuroscience; Signal processing algorithms; Silicon; Threshold voltage; Very large scale integration;
Conference_Titel :
Evolutionary Computation, 1994. IEEE World Congress on Computational Intelligence., Proceedings of the First IEEE Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1899-4
DOI :
10.1109/ICEC.1994.349962
