info presentación miembros líneas investigación publicaciones investigación tesis docencia

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

Categoria WoS
  • Applications
  • Artificial Neural Networks
  • Genetic Algorithms
Titulo: Training of Recurrent ANN with Time Decreased Activation by GA to the Forecast in Dynamic Problems
Tipo: congreso internacional
Congreso: World Multiconferece on Systemics, Cybernetics and Informatics (SCI 99/ISAS 99)
Fecha: 31-4 Agosto/7/1999
Lugar celebracion: Orlando, Florida (EEUU)
Volumen: Volume 3
Paginas: 463-469
ISBN: 980-07-5914-X
Libro: Proceedings SCI 99/ISAS 99


In this paper, we state an evolution of the recurrent ANN (RANN) to enforce the persistence of activations within the neurons to create activation contexts that generate correct outputs through time. In this new focus we want to file more information in the neuron`s connections. To do this, the connection`s representation goes from the unique values up to a function that generates the neuron`s output. The training process to this type of ANN has to calculate the gradient that identifies the function. To train this RANN we developed a GA based system that find the best gradient set to solve each problem.

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