Title :
Proposal for fuzzy optical adaptive resonance theory implementation
Author :
Kane, Jonathan S. ; Bartana, Ido
Author_Institution :
Opt. Signal Processing Branch, Hanscom AFB, MA, USA
fDate :
27 Jun-2 Jul 1994
Abstract :
Bartana et al. demonstrated a vector matrix-multiplier approach to optoelectronic implementations of ART1 type memories. In this paper we discuss a circuit modification which allows analog values to be processed with essentially the same architecture. The overall design concept is introduced and details are provided as to the specific operation of the associated fuzzy logic MIN circuit
Keywords :
ART neural nets; fuzzy neural nets; integrated optoelectronics; multiprocessor interconnection networks; optical neural nets; optical storage; ART1 neural net memories; fuzzy logic MIN circuit; fuzzy optical adaptive resonance theory implementation; optoelectronic implementations; vector matrix-multiplier; Adaptive optics; Circuits; Computer architecture; Correlators; Fuzzy logic; Optical filters; Proposals; Resonance; Subspace constraints; Testing;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374466
