For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Introducing an Adaptive VLR Algorithm Using Learning Automata for Multilayer Perceptron
Behbood MASHOUFI Mohammad Bagher MENHAJ Sayed A. MOTAMEDI Mohammad R. MEYBODI
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2003/03/01
Print ISSN: 0916-8532
Type of Manuscript: PAPER
multilayer neural network, backpropagation, variable learning rate, learning automata,
Full Text: PDF>>
One of the biggest limitations of BP algorithm is its low rate of convergence. The Variable Learning Rate (VLR) algorithm represents one of the well-known techniques that enhance the performance of the BP. Because the VLR parameters have important influence on its performance, we use learning automata (LA) to adjust them. The proposed algorithm named Adaptive Variable Learning Rate (AVLR) algorithm dynamically tunes the VLR parameters by learning automata according to the error changes. Simulation results on some practical problems such as sinusoidal function approximation, nonlinear system identification, phoneme recognition, Persian printed letter recognition helped us better to judge the merit of the proposed AVLR method.