Hardware Implementation of the Multifrequency Oscillation Learning Method for Analog Neural Networks

Hiroshi MIYAO  Masafumi KOGA  Takao MATSUMOTO  

IEICE TRANSACTIONS on Information and Systems   Vol.E76-D   No.6   pp.717-728
Publication Date: 1993/06/25
Online ISSN: 
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Bio-Cybernetics
neural networks,  learning method,  

Full Text: PDF>>
Buy this Article

High-speed learning of neural networks using the multifrequency oscillation method is demonstrated for first time. During the learning of an analog neural network integrated circuit implementing the exclusive-OR' logic, weight and threshold values converge to steady states within 2 ms for a learning speed of 2 mega-patterns per second.