Exact Solution for On-Line Learning in Multilayer Neural Networks
- 22 May 1995
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review Letters
- Vol. 74 (21) , 4337-4340
- https://doi.org/10.1103/physrevlett.74.4337
Abstract
We present an analytic solution to the problem of on-line gradient-descent learning for two-layer neural networks with an arbitrary number of hidden units in both teacher and student networks.Keywords
This publication has 5 references indexed in Scilit:
- Learning a rule in a multilayer neural networkJournal of Physics A: General Physics, 1993
- The statistical mechanics of learning a ruleReviews of Modern Physics, 1993
- Statistical mechanics of learning from examplesPhysical Review A, 1992
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989
- Infinite Number of Order Parameters for Spin-GlassesPhysical Review Letters, 1979