Affordable Access

deepdyve-link deepdyve-link
Publisher Website

Identification of finite state automata with a class of recurrent neural networks.

Authors
  • Won, Sung Hwan
  • Song, Iickho
  • Lee, Sun Young
  • Park, Cheol Hoon
Type
Published Article
Journal
IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council
Publication Date
Sep 01, 2010
Volume
21
Issue
9
Pages
1408–1421
Identifiers
DOI: 10.1109/TNN.2010.2059040
PMID: 20709639
Source
Medline
License
Unknown

Abstract

A class of recurrent neural networks is proposed and proven to be capable of identifying any discrete-time dynamical system. The application of the proposed network is addressed in the encoding, identification, and extraction of finite state automata (FSAs). Simulation results show that the identification of FSAs using the proposed network, trained by the hybrid greedy simulated annealing with a modified cost function in the training stage, generally exhibits better performance than the conventional identification procedures.

Report this publication

Statistics

Seen <100 times