For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Hardware Implementation of the Multifrequency Oscillation Learning Method for Analog Neural Networks
Hiroshi MIYAO Masafumi KOGA Takao MATSUMOTO
IEICE TRANSACTIONS on Information and Systems
Publication Date: 1993/06/25
Print ISSN: 0916-8532
Type of Manuscript: LETTER
neural networks, learning method,
Full Text: PDF>>
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.