On the analysis of dynamic feedback neural nets
Authors:
- 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
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 15 references indexed in Scilit:
- Dynamics of feedback neural nets with unsupervised learning1990
- A New Architecture For 2-D Array Neural Nets With An Electro-Optical Implementation1989
- Qualitative analysis and synthesis of a class of neural networksIEEE Transactions on Circuits and Systems, 1988
- Neural networks for nonlinear programmingIEEE Transactions on Circuits and Systems, 1988
- A formulation for the design of neural processors1988
- An introduction to computing with neural netsIEEE ASSP Magazine, 1987
- Optical Neural ComputersScientific American, 1987
- Neurons with graded response have collective computational properties like those of two-state neurons.Proceedings of the National Academy of Sciences, 1984
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982
- A logical calculus of the ideas immanent in nervous activityBulletin of Mathematical Biology, 1943