Global convergence of feedforward networks of learning automata

Autor:	V.V. Phansalkar, M.A.L. Thathachar
Rok vydání:	2003
Předmět:	Learning classifier system Theoretical computer science Learning automata Artificial neural network Computer science Competitive learning Feed forward Generalization error Langevin equation Convergence (routing) Reinforcement learning Automata theory Unsupervised learning Algorithm
Zdroj:	[Proceedings 1992] IJCNN International Joint Conference on Neural Networks.
DOI:	10.1109/ijcnn.1992.227089
Popis:	A feedforward network composed of units of teams of parameterized learning automata is considered as a model of a reinforcement learning system. The parameters of each learning automaton are updated using an algorithm consisting of a gradient following term and a random perturbation term. The algorithm is approximated by the Langevin equation. It is shown that it converges to the global maximum. The algorithm is decentralized and the units do not have any information exchange during updating. Simulation results on a pattern recognition problem show that reasonable rates of convergence can be obtained. >
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::0561ef5ecd936ebc017091f6df3ef36f https://doi.org/10.1109/ijcnn.1992.227089 Zobrazit plný text záznamu