Binary Second-Order Recurrent Neural Networks for Inferring Regular Grammars
Summary :
This paper proposes the binary second-order recurrent neural networks (BSRNN) equivalent to the modified finite automata (MFA) and presents the learning algorithm to construct the stable BSRNN for inferring regular grammar. This network combines two trends; one is to transform strings of a regular grammar into a recurrent neural network through training with no restriction of the number of neurons, the number of strings, and the length of string and the other is to directly transform itself into a finite automaton. Since neurons in the BSRNN employ a hard-limiter activation functions, the proposed BSRNN can become a good alternative of hardware implementation for regular grammars and finite automata as well as grammatical inference.
- Publication
- IEICE TRANSACTIONS on Information Vol.E83-D No.11 pp.1996-2007
- Publication Date
- 2000/11/25
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- PAPER
- Category
- Biocybernetics, Neurocomputing
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Soon-Ho JUNG, Hyunsoo YOON, "Binary Second-Order Recurrent Neural Networks for Inferring Regular Grammars" in IEICE TRANSACTIONS on Information,
vol. E83-D, no. 11, pp. 1996-2007, November 2000, doi: .
Abstract: This paper proposes the binary second-order recurrent neural networks (BSRNN) equivalent to the modified finite automata (MFA) and presents the learning algorithm to construct the stable BSRNN for inferring regular grammar. This network combines two trends; one is to transform strings of a regular grammar into a recurrent neural network through training with no restriction of the number of neurons, the number of strings, and the length of string and the other is to directly transform itself into a finite automaton. Since neurons in the BSRNN employ a hard-limiter activation functions, the proposed BSRNN can become a good alternative of hardware implementation for regular grammars and finite automata as well as grammatical inference.
URL: https://global.ieice.org/en_transactions/information/10.1587/e83-d_11_1996/_p
Copy
@ARTICLE{e83-d_11_1996,
author={Soon-Ho JUNG, Hyunsoo YOON, },
journal={IEICE TRANSACTIONS on Information},
title={Binary Second-Order Recurrent Neural Networks for Inferring Regular Grammars},
year={2000},
volume={E83-D},
number={11},
pages={1996-2007},
abstract={This paper proposes the binary second-order recurrent neural networks (BSRNN) equivalent to the modified finite automata (MFA) and presents the learning algorithm to construct the stable BSRNN for inferring regular grammar. This network combines two trends; one is to transform strings of a regular grammar into a recurrent neural network through training with no restriction of the number of neurons, the number of strings, and the length of string and the other is to directly transform itself into a finite automaton. Since neurons in the BSRNN employ a hard-limiter activation functions, the proposed BSRNN can become a good alternative of hardware implementation for regular grammars and finite automata as well as grammatical inference.},
keywords={},
doi={},
ISSN={},
month={November},}
Copy
TY - JOUR
TI - Binary Second-Order Recurrent Neural Networks for Inferring Regular Grammars
T2 - IEICE TRANSACTIONS on Information
SP - 1996
EP - 2007
AU - Soon-Ho JUNG
AU - Hyunsoo YOON
PY - 2000
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E83-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2000
AB - This paper proposes the binary second-order recurrent neural networks (BSRNN) equivalent to the modified finite automata (MFA) and presents the learning algorithm to construct the stable BSRNN for inferring regular grammar. This network combines two trends; one is to transform strings of a regular grammar into a recurrent neural network through training with no restriction of the number of neurons, the number of strings, and the length of string and the other is to directly transform itself into a finite automaton. Since neurons in the BSRNN employ a hard-limiter activation functions, the proposed BSRNN can become a good alternative of hardware implementation for regular grammars and finite automata as well as grammatical inference.
ER -
English
