Title :
MOS circuit for nonlinear Hebbian learning
Author :
Cohen, M.H. ; Andreou, A.G.
Author_Institution :
John Hopkins Univ., Baltimore, MD, USA
fDate :
4/23/1992 12:00:00 AM
Abstract :
An analogue MOS circuit that implements a nonlinear Hebbian learning rule is presented. The circuit has two differential inputs (voltages) and yields an output (current) which approximates the product of a cubic and hyperbolic tangent functions of the two input voltages. This has been successfully incorporated in an analogue integrated circuit implementation of the Herault-Jutten neuromorphic network.
Keywords :
MOS integrated circuits; learning systems; linear integrated circuits; neural nets; Herault-Jutten neuromorphic network; analogue MOS circuit; cubic tangent functions; differential inputs; hyperbolic tangent functions; nonlinear Hebbian learning;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19920512
