State Automata Extraction from Recurrent Neural Nets using k-Means and Fuzzy Clustering

  • Authors:

  • Adelmo Luis Cechin;Denise Regina Pechmann Simon;Klaus Stertz

  • Affiliations:

  • -;-;-

  • Venue:
  • SCCC '03 Proceedings of the XXIII International Conference of the Chilean Computer Science Society
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents the use of a recurrent neuralnetwork to learn the dynamical behavior of the invertedpendulum and from this network to extract a finite stateautomata. Two clustering methods are compared for theautomata extraction: the K-means method, and theconstruction of fuzzy membership functions. It is shownthat the number of states for the fuzzy clustering methodinduces much less states than the K-means method.