DocumentCode
2970921
Title
A circuit model for the adaptive properties of neural networks
Author
Soma, Mani
Author_Institution
Dept. of Electr. Eng., Washington Univ., Seattle, WA, USA
fYear
1989
fDate
14-17 Nov 1989
Firstpage
895
Abstract
A simple probabilistic model of a two-layer neural net is proposed to quantize the fault tolerance characteristics of the network from circuit design perspectives. While the model assumes very simple distribution functions and an elementary architecture, the results illuminate the design tradeoffs that must be considered, especially in VLSI implementations. The methods to quantize fault tolerance that are presented are applicable to more complicated probability distributions and architectures
Keywords
VLSI; adaptive systems; neural nets; reliability; VLSI implementations; adaptive properties; circuit model; design tradeoffs; elementary architecture; fault tolerance characteristics; probabilistic model; two-layer neural net; Circuit faults; Costs; Fault tolerance; Fault tolerant systems; Integrated circuit interconnections; Logic; Multiprocessor interconnection networks; Neural networks; Probability distribution; Redundancy;
fLanguage
English
Publisher
ieee
Conference_Titel
Systems, Man and Cybernetics, 1989. Conference Proceedings., IEEE International Conference on
Conference_Location
Cambridge, MA
Type
conf
DOI
10.1109/ICSMC.1989.71425
Filename
71425
Link To Document