On the analysis of dynamic feedback neural nets

1 February 1991

journal article
Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems

Vol. 38 (2) , 196-201
https://doi.org/10.1109/31.68297

Abstract

A formulation for dynamic feedback neural networks of the Hopfield type is presented. A description is given of the general design framework used, in which a neural network would only have a finite number of memories. Some basic properties of the nonzero equilibria as well as the (unstable) equilibrium point at zero in the proposed framework are also discussed.

Keywords

This publication has 25 references indexed in Scilit:

An analog MOS implementation of the synaptic weights for feedback neural nets
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2003
A formulation for 2-D array neural nets for electro-optical implementation
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2003
An analog MOS implementation of the synaptic weights for feedforward/feedback neural nets
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2003
A model of neural circuits for programmable VLSI implementation
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2003
Programmable analog VLSI neural circuits for control
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2003
Some properties of dynamic feedback neural nets
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2003
New artificial neural net models: basic theory and characteristics
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2002
Design of neural network systems from custom analog VLSI chips
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2002
An all-MOS analog feedforward neural circuit with learning
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2002
An introduction to computing with neural nets
IEEE ASSP Magazine, 1987