Comments on “Constructive learning of recurrent neural networks: limitations of recurrent cascade correlation and a simple solution”

  • Authors:

  • S. C. Kremer

  • Affiliations:

  • Communication Res. Centre, Ottawa, Ont.

  • Venue:
  • IEEE Transactions on Neural Networks
  • Year:
  • 1996

Quantified Score

Hi-index 0.00

Visualization

Abstract

Giles et al. (1995) have proven that Fahlman's recurrent cascade correlation (RCC) architecture is not capable of realizing finite state automata that have state-cycles of length more than two under a constant input signal. This paper extends the conclusions of Giles et al. by showing that there exists a corollary to their original proof which identifies a large second class of automata, that is also unrepresentable by RCC