Search History  -  Selected Records  -  My Profile  -  My AlertsEnd Session
Easy SearchQuick SearchExpert SearchThesauruseBook SearchAsk an ExpertHelp
Abstract  -  Detailed
               
Record 68 from Compendex for: ((meybodi) WN All fields), 1790-2007
Check record to add to Selected Records
68.Adaptive LRBP using learning automata for neural networks
Mashoufi, B. (Electrical Engineering Department, Amirkabir University of Technology); Menhaj, Mohammad B.; Motamedi, Sayed A.; Meybodi, Mohammad R. Source: Advances in Neural Networks and Applications, Advances in Neural Networks and Applications, 2001, p 280-286
ISBN: 9608052262
Publisher: World Scientific and Engineering Academy and Society


Abstract: One of the biggest limitations of BP algorithm is its low rate of convergence. In this paper, Variable Learning Rate (VLR) algorithm and learning automata based learning rate adaptation algorithms are described and compared with each other. Because the VLR parameters have important influence in its performance, we use learning automata for adjusting them. In the proposed algorithm named as Adaptive Variable Learning Rate (AVLR) algorithm, VLR parameters are changed dynamically according to error changes by learning automata. Simulation results on a second order discrete time nonlinear function approximation problem highlight better the merit of the proposed AVLR.
(19 refs.)

Ei controlled terms:
Neural networks  -  Learning systems  -  Algorithms  -  Iterative methods  -  Automata theory  -  Approximation theory  -  Vectors  -  Backpropagation

Classification Code:   
723.4 Artificial Intelligence  -  921.6 Numerical Methods  -  721.1 Computer Theory, Includes Formal Logic, Automata Theory, Switching Theory, Programming Theory  -  921.1 Algebra

Database: Compendex

  Full-text and Local Holdings Links

About Ei  -  About Engineering Village  -  Feedback  -  Privacy Policy
© 2006 Elsevier Inc. All rights reserved.