|58.||A note on learning automata-based schemes for adaptation of BP parameters|
Meybodi, M.R. (Soft Computing Laboratory, Computer Engineering Department, Amirkabir University of Technology); Beigy, H. Source: Neurocomputing, v 48, October, 2002, p 957-974
ISSN: 0925-2312 CODEN: NRCGEO
Publisher: Elsevier Science B.V.
Abstract: In this paper, we study the ability of learning automata-based schemes in escaping from local minima when standard backpropagation (BP) fails to find the global minima. It is demonstrated through simulation that learning automata-based schemes compared to other schemes such as SAB, Super SAB, Fuzzy BP, adaptive steepness method, and variable learning rate method have a higher ability to escape from local minima. © 2002 Elsevier Science B.V. All rights reserved. (31 refs.)
Ei controlled terms: Automata theory - Learning systems - Neural networks - Backpropagation - Computer simulation
Classification Code: 721.1 Computer Theory, Includes Formal Logic, Automata Theory, Switching Theory, Programming Theory - 723.4 Artificial Intelligence - 723.5 Computer Applications