Learning-parameter adjustment in neural networks
- 1 June 1992
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review A
- Vol. 45 (12) , 8885-8893
- https://doi.org/10.1103/physreva.45.8885
Abstract
We present a learning-parameter adjustment algorithm, valid for a large class of learning rules in neural-network literature. The algorithm follows directly from a consideration of the statistics of the weights in the network. The characteristic behavior of the algorithm is calculated, both in a fixed and a changing environment. A simple example, Widrow-Hoff learning for statistical classification, serves as an illustration.Keywords
This publication has 8 references indexed in Scilit:
- Learning processes in neural networksPhysical Review A, 1991
- A convergence theorem for Grossberg learningNeural Networks, 1990
- Learning representations by back-propagating errorsNature, 1986
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982
- Self-organized formation of topologically correct feature mapsBiological Cybernetics, 1982
- Stochastic Approximation Methods for Constrained and Unconstrained SystemsPublished by Springer Nature ,1978
- Analysis of recursive stochastic algorithmsIEEE Transactions on Automatic Control, 1977
- A Theory of Adaptive Pattern ClassifiersIEEE Transactions on Electronic Computers, 1967