Introducing an Adaptive VLR Algorithm Using Learning Automata for Multilayer Perceptron

Behbood MASHOUFI; Mohammad Bagher MENHAJ; Sayed A. MOTAMEDI; Mohammad R. MEYBODI

Introducing an Adaptive VLR Algorithm Using Learning Automata for Multilayer Perceptron

Behbood MASHOUFI, Mohammad Bagher MENHAJ, Sayed A. MOTAMEDI, Mohammad R. MEYBODI

Full Text Views

0

Share
Cite this

Summary :

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.

Publication: IEICE TRANSACTIONS on Information Vol.E86-D No.3 pp.594-609

Publication Date: 2003/03/01

Publicized

Online ISSN

DOI

Type of Manuscript: PAPER

Category: Algorithms

Cite this

Copy

Behbood MASHOUFI, Mohammad Bagher MENHAJ, Sayed A. MOTAMEDI, Mohammad R. MEYBODI, "Introducing an Adaptive VLR Algorithm Using Learning Automata for Multilayer Perceptron" in IEICE TRANSACTIONS on Information, vol. E86-D, no. 3, pp. 594-609, March 2003, doi: .
Abstract: 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.
URL: https://globals.ieice.org/en_transactions/information/10.1587/e86-d_3_594/_p

Copy

@ARTICLE{e86-d_3_594,
author={Behbood MASHOUFI, Mohammad Bagher MENHAJ, Sayed A. MOTAMEDI, Mohammad R. MEYBODI, },
journal={IEICE TRANSACTIONS on Information},
title={Introducing an Adaptive VLR Algorithm Using Learning Automata for Multilayer Perceptron},
year={2003},
volume={E86-D},
number={3},
pages={594-609},
abstract={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.},
keywords={},
doi={},
ISSN={},
month={March},}

Copy

TY - JOUR
TI - Introducing an Adaptive VLR Algorithm Using Learning Automata for Multilayer Perceptron
T2 - IEICE TRANSACTIONS on Information
SP - 594
EP - 609
AU - Behbood MASHOUFI
AU - Mohammad Bagher MENHAJ
AU - Sayed A. MOTAMEDI
AU - Mohammad R. MEYBODI
PY - 2003
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E86-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2003
AB - 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.
ER -