ML Anthology

RCC Cannot Compute Certain FSA, Even with Arbitrary Transfer Functions

Mark Ring
NeurIPS 1997 pp. 619-625
/neurips/1997/ring1997neurips-rcc/

Abstract

Existing proofs demonstrating the computational limitations of Re(cid:173) current Cascade Correlation and similar networks (Fahlman, 1991; Bachrach, 1988; Mozer, 1988) explicitly limit their results to units having sigmoidal or hard-threshold transfer functions (Giles et aI., 1995; and Kremer, 1996). The proof given here shows that for any finite, discrete transfer function used by the units of an RCC network, there are finite-state automata (FSA) that the network cannot model, no matter how many units are used. The proof also applies to continuous transfer functions with a finite number of fixed-points, such as sigmoid and radial-basis functions.

PDF NeurIPS Semantic Scholar

Cite

Text

Ring. "RCC Cannot Compute Certain FSA, Even with Arbitrary Transfer Functions." Neural Information Processing Systems, 1997.

Markdown

[Ring. "RCC Cannot Compute Certain FSA, Even with Arbitrary Transfer Functions." Neural Information Processing Systems, 1997.](https://mlanthology.org/neurips/1997/ring1997neurips-rcc/)

BibTeX

@inproceedings{ring1997neurips-rcc,
  title     = {{RCC Cannot Compute Certain FSA, Even with Arbitrary Transfer Functions}},
  author    = {Ring, Mark},
  booktitle = {Neural Information Processing Systems},
  year      = {1997},
  pages     = {619-625},
  url       = {https://mlanthology.org/neurips/1997/ring1997neurips-rcc/}
}