Adaptation of Parameters of BP Algorithm Using Learning Automata

d Articles >> Table of Contents >> Abstract VI Brazilian Symposium on Neural Networks (SBRN'00) p. 24 Adaptation of Parameters of BP Algorithm Using Automata Hamid Beigy, Amirkabir University of Technology M.R. Meybodi, Amirkabir University of Technology Full Article Text: DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/SBRN Send link to a friend ADD TO: Blink Del.icio.us Digg Furl Google Simpy Backpropagation (BP) algorithm is a systematic method for training multilay Despite of the many successful applications of backpropagation, it has many problems, it may require a long time to train the networks, and it may not tra time can be the result of the non-optimal parameters. It is not easy to choose parameters for a particular problem. In this paper, by interconnection of fixe automata (FSLA) to the feedforward neural networks, we apply learning auto adjusting these parameters based on the observation of random response of n main motivation in using learning a...

• Type: Conference
• Year: 2000
• Where: SBRN
• Authors: Hamid Beigy, Mohammad Reza Meybodi
• Keywords: Amirkabir University, Neural Networks, Parameters, SBRN 2000