On Super-Turing Neural Computation

Details

Serval ID
serval:BIB_2C7C91742208
Type
Inproceedings: an article in a conference proceedings.
Collection
Publications
Institution
Title
On Super-Turing Neural Computation
Title of the conference
Advances in Cognitive Neurodynamics (IV)
Author(s)
Cabessa J., Villa A.E.P.
Publisher
Springer Netherlands
Address
Sweden
ISBN
978-94-017-9547-0
978-94-017-9548-7
ISSN
2213-3569
2213-3577
Publication state
Published
Issued date
2015
Peer-reviewed
Oui
Volume
4
Series
Advances in Cognitive Neurodynamics
Pages
307-312
Language
english
Abstract
In this paper, we provide a historical survey of the most significant results concerning the computational power of neural models. We distinguish three important periods: first, the early works from McCulloch and Pitts, Kleene, and Minky, where the computational equivalence between Boolean recurrent neural networks and finite state automata is established. Secondly, the two breakthroughs by Siegelmann and Sontag showing the Turing universality of rational-weighted neural networks, and the super-Turing capabilities of analog recurrent neural networks. Thirdly, the recent results by Cabessa, Siegelmann and Villa revealing the super-Turing computational potentialities of interactive and evolving recurrent neural networks.
Keywords
Neural computation, Recurrent neural networks, Finite automata, Turing machines, Turing machines with advice, super-Turing
Web of science
Create date
03/08/2017 16:15
Last modification date
20/08/2019 13:11
Usage data