Selecting the Best Significant Fragment to the Incremental Heteroassociative Neural Network (RHI)

  • J. M. García Chamizo
  • R. Satorre Cuerda
  • F. Ibarra Picó
  • S. Cuenca Asensi


The generality of the artificial neural networks models infers the requests based in the totality of the characteristics of the patterns. The RHI model infers just with a limited set of this characteristics, the significant fragment. This reason make RHI really appropriated by resolution of control and active vision problem. Although RHI model present high sensibility to distortion. In this paper it is developed the formalism to obtain the significant fragment in such a way it improve the noise tolerance.


Artificial Neural Network Model Equation System Learning Pattern Recognition Error Bidirectional Associative Memory 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    García-Chamizo, J.M.;Crespo Lorente,A. “Redes Neuronales Heteroasociativas Increméntales”. IFIP Congress’92, Septiembre 1992Google Scholar
  2. [2]
    García-Chamizo, J.M.; Crespo-Lorente, A.; Rizo Aldeguer,R.. “Extracción de fragmentos significativos de patrones para su posterior reconocimiento mediante Redes Neuronales RHI”. Jornadas sobre Redes Neuronales 26–30 Octubre 1992. Centro Nacional de Microelectrónica (CSIC). Instituto de Neurociencias (UA).Google Scholar
  3. [3]
    García-Chamizo, J.M.; Crespo-Lorente, A.; Rizo-Aldeguer, R. “Output Pattern Recalling Aided By Themselves: Incremental Heteroassociative Networks”. Proceedings of the IJCNN, Beijing, November 1992Google Scholar
  4. [4]
    García-Chamizo. “Semicoberturas heterogéneas de regiones bidimensionales morfológicamente no restringidas. Modelado conexionista aplicado”. Doctoral Dissertation, February, 1994Google Scholar
  5. [5]
    Garcia Chamizo, J.M.; Mora Pascual, J.; Rizo Aldeguer, R.; Ledesma Latorre, B. “An incidence angle detection system for automatic assembly tools using the RHI network model”. IEEE IAS International Conference on Industrial Automation and Control, Hyderabad (India ), 1995.Google Scholar
  6. [6]
    Grossberg, S. (editor). “The Adaptive Brain”. Elsevier Science Publishing Co., Inc, 1987Google Scholar
  7. [7]
    Ibarra Pico, F; Garcia Chamizo, J.M. “A Generalized Bidirectional Associative Memory with a Hidden Orthogonal Layer”. ICANN’94, Sorrento, May 1994Google Scholar
  8. [8]
    Kandel, E. R.; Schwart, J. H. “Principles of Neural Science”. Elsevier Science Publishing Co., Inc., 1985.Google Scholar
  9. [9]
    Kohomen, T. “Self-Organization and Associative Memory”. Springer-Verlag, 2nd. edition, 1988Google Scholar
  10. [10]
    Kosko, B. “Adaptive Bidirectional Associative Memories”. Applied Optics, vol 26, n 23, Dec. 1987Google Scholar
  11. [11]
    Kosko, B. “Bidirectional Associative Memories ”. IEEE Transactions on Systems, Man & Cybernetics, vol 18, n1, Jan./Feb. 1988Google Scholar
  12. [12]
    Lancaster, P. & Tismenetsky, M. “The Theory of Matrices”. Academic Press, 1985Google Scholar
  13. [13]
    Pao, Y. “Adaptive Pattern Recognition and Neural Networks”. Addison-Wesley Publishing Company, Inc, 1989MATHGoogle Scholar
  14. [14]
    Torregrosa, V. “Modelo Neuronal de Memoria Asociativa Ortonomalizada Adaptativa”. P.F.C. U.P.V., 1993Google Scholar
  15. [15]
    W. Thomas Miller,III;Richard S.Sutton; Paul I. Werbos. “Neural Networks For Control”. Institute of Technology. Massachusetts, 1990Google Scholar
  16. [16]
    Zurada, J.M. “Introduction to Artificial Neural Systems”. West Publishing Company, 1992Google Scholar

Copyright information

© Springer-Verlag/Wien 1995

Authors and Affiliations

  • J. M. García Chamizo
    • 1
  • R. Satorre Cuerda
    • 1
  • F. Ibarra Picó
    • 1
  • S. Cuenca Asensi
    • 1
  1. 1.Departamento de Tecnología Informática y ComputaciónUniversidad de AlicanteAlicanteSpain

Personalised recommendations