Representation and induction of finite state machines using time-delay neural networks

Daniel S. Clouse; C. Lee Giles; Bill G. Horne; Garrison W. Cottrell

Representation and induction of finite state machines using time-delay neural networks

Daniel S. Clouse, C. Lee Giles, Bill G. Horne, Garrison W. Cottrell

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This work investigates the representational and inductive capabilities of time-delay neural networks (TDNNs) in general, and of two subclasses of TDNN, those with delays only on the inputs (IDNN), and those which include delays on hidden units (HDNN). Both architectures are capable of representing the same class of languages, the definite memory machine (DMM) languages, but the delays on the hidden units in the HDNN helps it outperform the IDNN on problems composed of repeated features over short time windows.

Original language	English (US)
Title of host publication	Advances in Neural Information Processing Systems 9 - Proceedings of the 1996 Conference, NIPS 1996
Publisher	Neural information processing systems foundation
Pages	403-409
Number of pages	7
ISBN (Print)	0262100657, 9780262100656
State	Published - Jan 1 1997
Event	10th Annual Conference on Neural Information Processing Systems, NIPS 1996 - Denver, CO, United States Duration: Dec 2 1996 → Dec 5 1996

Publication series

Name	Advances in Neural Information Processing Systems
ISSN (Print)	1049-5258

Other

Other	10th Annual Conference on Neural Information Processing Systems, NIPS 1996
Country	United States
City	Denver, CO
Period	12/2/96 → 12/5/96

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Information Systems
Signal Processing

Fingerprint Dive into the research topics of 'Representation and induction of finite state machines using time-delay neural networks'. Together they form a unique fingerprint.

Cite this

Clouse, D. S., Giles, C. L., Horne, B. G., & Cottrell, G. W. (1997). Representation and induction of finite state machines using time-delay neural networks. In Advances in Neural Information Processing Systems 9 - Proceedings of the 1996 Conference, NIPS 1996 (pp. 403-409). (Advances in Neural Information Processing Systems). Neural information processing systems foundation.

Clouse, Daniel S. ; Giles, C. Lee ; Horne, Bill G. ; Cottrell, Garrison W. / Representation and induction of finite state machines using time-delay neural networks. Advances in Neural Information Processing Systems 9 - Proceedings of the 1996 Conference, NIPS 1996. Neural information processing systems foundation, 1997. pp. 403-409 (Advances in Neural Information Processing Systems).

@inproceedings{7ad82343eae144d5a72b5608385d1610,

title = "Representation and induction of finite state machines using time-delay neural networks",

abstract = "This work investigates the representational and inductive capabilities of time-delay neural networks (TDNNs) in general, and of two subclasses of TDNN, those with delays only on the inputs (IDNN), and those which include delays on hidden units (HDNN). Both architectures are capable of representing the same class of languages, the definite memory machine (DMM) languages, but the delays on the hidden units in the HDNN helps it outperform the IDNN on problems composed of repeated features over short time windows.",

author = "Clouse, {Daniel S.} and Giles, {C. Lee} and Horne, {Bill G.} and Cottrell, {Garrison W.}",

year = "1997",

month = jan,

day = "1",

language = "English (US)",

isbn = "0262100657",

series = "Advances in Neural Information Processing Systems",

publisher = "Neural information processing systems foundation",

pages = "403--409",

booktitle = "Advances in Neural Information Processing Systems 9 - Proceedings of the 1996 Conference, NIPS 1996",

note = "10th Annual Conference on Neural Information Processing Systems, NIPS 1996 ; Conference date: 02-12-1996 Through 05-12-1996",

}

Clouse, DS, Giles, CL, Horne, BG & Cottrell, GW 1997, Representation and induction of finite state machines using time-delay neural networks. in Advances in Neural Information Processing Systems 9 - Proceedings of the 1996 Conference, NIPS 1996. Advances in Neural Information Processing Systems, Neural information processing systems foundation, pp. 403-409, 10th Annual Conference on Neural Information Processing Systems, NIPS 1996, Denver, CO, United States, 12/2/96.

Representation and induction of finite state machines using time-delay neural networks. / Clouse, Daniel S.; Giles, C. Lee; Horne, Bill G.; Cottrell, Garrison W.

Advances in Neural Information Processing Systems 9 - Proceedings of the 1996 Conference, NIPS 1996. Neural information processing systems foundation, 1997. p. 403-409 (Advances in Neural Information Processing Systems).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Representation and induction of finite state machines using time-delay neural networks

AU - Clouse, Daniel S.

AU - Giles, C. Lee

AU - Horne, Bill G.

AU - Cottrell, Garrison W.

PY - 1997/1/1

Y1 - 1997/1/1

N2 - This work investigates the representational and inductive capabilities of time-delay neural networks (TDNNs) in general, and of two subclasses of TDNN, those with delays only on the inputs (IDNN), and those which include delays on hidden units (HDNN). Both architectures are capable of representing the same class of languages, the definite memory machine (DMM) languages, but the delays on the hidden units in the HDNN helps it outperform the IDNN on problems composed of repeated features over short time windows.

AB - This work investigates the representational and inductive capabilities of time-delay neural networks (TDNNs) in general, and of two subclasses of TDNN, those with delays only on the inputs (IDNN), and those which include delays on hidden units (HDNN). Both architectures are capable of representing the same class of languages, the definite memory machine (DMM) languages, but the delays on the hidden units in the HDNN helps it outperform the IDNN on problems composed of repeated features over short time windows.

UR - http://www.scopus.com/inward/record.url?scp=84899032195&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899032195&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84899032195

SN - 0262100657

SN - 9780262100656

T3 - Advances in Neural Information Processing Systems

SP - 403

EP - 409

BT - Advances in Neural Information Processing Systems 9 - Proceedings of the 1996 Conference, NIPS 1996

PB - Neural information processing systems foundation

T2 - 10th Annual Conference on Neural Information Processing Systems, NIPS 1996

Y2 - 2 December 1996 through 5 December 1996

ER -