Back to Search
Start Over
A Modified Hebbian Algorithm for Analog VLSI Neural Network Implementation.
- Source :
-
Electronics & Communications in Japan, Part 3: Fundamental Electronic Science . Nov93, Vol. 76 Issue 11, p20-29. 10p. - Publication Year :
- 1993
-
Abstract
- Various studies on learning rules for neural networks have been done. However, most of those do not consider the hardware implementation, which is a great drawback in the LSI implementation of neural networks with learning capability. From such a viewpoint, this paper proposes a self-organizing learning rule by modifying the Hebbian learning rule. This rule can be implemented easily on an analog VLSI chip as an on-chip learning rule. The self-organizing ability of the system is verified by simulation experiments. It is shown from the experiment that the learning speed is improved by a factor of 2 to 3, and it is possible to avoid the sudden termination of the learning and the divergence of the synaptic weights. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 10420967
- Volume :
- 76
- Issue :
- 11
- Database :
- Academic Search Index
- Journal :
- Electronics & Communications in Japan, Part 3: Fundamental Electronic Science
- Publication Type :
- Academic Journal
- Accession number :
- 13709007