Self-organizing neurocontrol

T. Fomin, Cs Szepesvari, A. Lorincz

Research output: Contribution to conferencePaper

4 Citations (Scopus)

Abstract

Self-organizing neural network solutions to control problems are described. Competitive networks create spatial filters and geometry connections in a self-organizing fashion. The goal position, the obstacles and the object under control all create neural activities through the filters. Spreading activation that discriminates between the controlled object, the goal position and the obstacles is utilized on the internal representation. Local self-training method and Hebbian learning develops the self-organizing control connections. The algorithm provides maneouvring capability in unseen scenes.

Original languageEnglish
Pages2777-2780
Number of pages4
Publication statusPublished - Dec 1 1994
EventProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) - Orlando, FL, USA
Duration: Jun 27 1994Jun 29 1994

Other

OtherProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7)
CityOrlando, FL, USA
Period6/27/946/29/94

    Fingerprint

ASJC Scopus subject areas

  • Software

Cite this

Fomin, T., Szepesvari, C., & Lorincz, A. (1994). Self-organizing neurocontrol. 2777-2780. Paper presented at Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7), Orlando, FL, USA, .