Finite State Automata that Recurrent Cascade-Correlation Cannot Represent

Stefan C. Kremer

Advances in Neural Information Processing Systems 8 (NIPS 1995)

This paper relates the computational power of Fahlman' s Recurrent Cascade Correlation (RCC) architecture to that of fInite state automata (FSA). While some recurrent networks are FSA equivalent, RCC is not. The paper presents a theoretical analysis of the RCC architecture in the form of a proof describing a large class of FSA which cannot be realized by RCC.