A general weight matrix formulation using optimal control

1 May 1991

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

Vol. 2 (3) , 378-394
https://doi.org/10.1109/72.97914

Abstract

Classical methods from optimal control theory are used in deriving general forms for neural network weights. The network learning or application task is encoded in a performance index of a general structure. Consequently, different instances of this performance index lead to special cases of weight rules, including some well-known forms. Comparisons are made with the outer product rule, spectral methods, and recurrent back-propagation. Simulation results and comparisons are presented.

Keywords

This publication has 11 references indexed in Scilit:

A massively parallel architecture for a self-organizing neural pattern recognition machine
Published by Elsevier ,2005
On the capacity of associative memories with linear threshold functions
IEEE Transactions on Information Theory, 1989
Linear and logarithmic capacities in associative neural networks
IEEE Transactions on Information Theory, 1989
Information capacity of associative memories
IEEE Transactions on Information Theory, 1989
Qualitative analysis and synthesis of a class of neural networks
IEEE Transactions on Circuits and Systems, 1988
Layered neural nets for pattern recognition
IEEE Transactions on Acoustics, Speech, and Signal Processing, 1988
Absolute Stability of Global Pattern Formation and Parallel Memory Storage by Competitive Neural Networks
Published by Elsevier ,1987
Information storage and retrieval in spin-glass like neural networks
Journal de Physique Lettres, 1985
Neural networks and physical systems with emergent collective computational abilities.
Proceedings of the National Academy of Sciences, 1982
Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition
IEEE Transactions on Electronic Computers, 1965