.: Marcos Gestal :.     -----


Datos de la Publicación:

Marcos Gestal, Juan Ramón Rabuñal, Julián Dorado, Javier Pereira
Título: Description of RANNs and their Generalisation Capabilities by Means of Rule Extraction by Genetic Programming
Congreso: IASTED International Conference on Artificial Intelligence and Soft Computing (ASC 2006)
Lugar Celebración: Palma de Mallorca (España)
Fecha Celebración: 28-30 de Agosto de 2006
Publicación: Proceedings of the 10th IASTED International Conference on Artificial Intelligence and Soft Computing
ISBN: 0-88986-610-4
Páginas: 323-328
Editorial: Acta Press
Fecha Publicación: Agosto 2006
Congreso indexado en Australian Ranking of ICT Conference (CORE): categoria C
Congreso indexado en Computer Science Conference Ranking: 0.57 (48/701)


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.