info presentación miembros líneas investigación publicaciones investigación tesis docencia

[Articulos Revista] [Articulos Congreso] [Reports] [Libros] [Capitulos Libro] [Todo] [Resumen]

Categoria WoS
  • Evolutionary Computation
  • Genetic Programming
Titulo: Description of RANNs and their Generalisation Capabilities by Means of Rule Extraction by Genetic Programming
Tipo: congreso internacional
Congreso: IASTED International Conference on Artificial Intelligence and Soft Computing (ASC 2006)
Fecha: 28-30/8/2006
Lugar celebracion: Palma de Mallorca (España)
Paginas: 323-328
ISSN: 1482-7913
ISBN: 0-88986-610-4
Libro: Proceedings of the 10th IASTED International Conference on Artificial Intelligence and Soft Computing
Editorial: Acta Press


Artificial Neural Networks have achieved satisfactory results in different fields such as example classification or image identification. Real-world processes usually have a temporal evolution, and they are the type of processes where Recurrent Networks have special success. Nevertheless they are still reluctantly used, mainly due to the fact that they do not adequately justify their response. But, if ANNs offer good results, why giving them up? Suffice it to find a method that might search an explanation to the outputs that the ANN provides. This work presents a technique, totally independent from ANN architecture and the learning algorithm used, which makes possible the justification of the ANN outputs by means of expression trees.

    .: SABIA :.  Sistemas Adaptativos y Bioinspirados en Inteligencia Artificial