1995 | OriginalPaper | Buchkapitel
Selecting the Best Significant Fragment to the Incremental Heteroassociative Neural Network (RHI)
verfasst von : J. M. García Chamizo, R. Satorre Cuerda, F. Ibarra Picó, S. Cuenca Asensi
Erschienen in: Artificial Neural Nets and Genetic Algorithms
Verlag: Springer Vienna
Enthalten in: Professional Book Archive
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
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.