Logic circuits of variable function using neural networks and their methodof calculating synaptic weights
Citation
M. Teramura et al., Logic circuits of variable function using neural networks and their methodof calculating synaptic weights, ELEC C JP 3, 83(1), 2000, pp. 14-20
Categorie Soggetti
Eletrical & Eletronics Engineeing
Journal title
ELECTRONICS AND COMMUNICATIONS IN JAPAN PART III-FUNDAMENTAL ELECTRONIC SCIENCE
SICI code
1042-0967(2000)83:1<14:LCOVFU>2.0.ZU;2-D
Abstract
The authors previously reported on a variable logic circuit using a neural
network (NN), in which logic operation was controlled by an analog voltage,
In that design, the synaptic weights were determined by the error back-pro
pagation (BP) algorithm. Then, logic outputs outside the specification were
produced between logic outputs with Hamming distances of two or more. This
paper proposes a design of NN in which no logic outside the specification
is output, together with a method of calculating the synaptic weights. Base
d on the correspondence between the change of the output logic and the cont
rol voltage, the necessary number of hidden-layer neurons can be defined. T
he computation time for the synaptic weights is reduced. By constructing an
NN circuit by the proposed method, it is verified that the desired operati
on is. realized. (C) 1999 Scripts Technica.