Learnability in sequential RAM-based neural networks
Marcílio C. P. de Souto, Paulo J. L. Adeodato · 2002
It is well known that, in a broad sense, recurrent neural networks are equivalent to Turing machines. However, in general, such 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 are proved to have limitations which prevent the networks from attaining their computability.