Learnability in Sequential RAM-based Neural Networks

Marcílio Carlos Pereira de SoutoPaulo J. L. Adeodato

It is well known that, in a broad sense, recurrent neural networks are equivalent to Turing machines. However, in general, such a computational power has not been achieved by the current learning algorithms. In this paper, the learning capability of the existing algorithms for sequential {RAM-based} neural networks is analysed. These learning algorithms will be proved to have limitations which prevent the networks from attaining their computability.

Caso o link acima esteja inválido, faça uma busca pelo texto completo na Web: Buscar na Web

Biblioteca Digital Brasileira de Computação - Contato:
     Mantida por: