Dynamic recurrent neural networks: theory and applications

C. Lee Giles; Gary M. Kuhn; Ronald J. Williams

doi:10.1109/tnn.1994.8753425

Dynamic recurrent neural networks: theory and applications

C. Lee Giles, Gary M. Kuhn, Ronald J. Williams

Research output: Contribution to journal › Article › peer-review

164 Scopus citations

Abstract

Illustrated in this paper are the scientific trends of the early work in recurrent neural networks and the mathematics of training when at least some recurrent terms of the network derivatives can be non-zero.

Original language	English (US)
Pages (from-to)	153-156
Number of pages	4
Journal	IEEE Transactions on Neural Networks
Volume	5
Issue number	2
DOIs	https://doi.org/10.1109/tnn.1994.8753425
State	Published - 1994

All Science Journal Classification (ASJC) codes

Software
Computer Science Applications
Computer Networks and Communications
Artificial Intelligence

Access to Document

10.1109/tnn.1994.8753425

Cite this

@article{b67e5e7091834c0380cbfd6e040af2c5,

title = "Dynamic recurrent neural networks: theory and applications",

abstract = "Illustrated in this paper are the scientific trends of the early work in recurrent neural networks and the mathematics of training when at least some recurrent terms of the network derivatives can be non-zero.",

author = "Giles, {C. Lee} and Kuhn, {Gary M.} and Williams, {Ronald J.}",

year = "1994",

doi = "10.1109/tnn.1994.8753425",

language = "English (US)",

volume = "5",

pages = "153--156",

journal = "IEEE Transactions on Neural Networks",

issn = "1045-9227",

publisher = "IEEE Computational Intelligence Society",

number = "2",

}

TY - JOUR

T1 - Dynamic recurrent neural networks

T2 - theory and applications

AU - Giles, C. Lee

AU - Kuhn, Gary M.

AU - Williams, Ronald J.

PY - 1994

Y1 - 1994

N2 - Illustrated in this paper are the scientific trends of the early work in recurrent neural networks and the mathematics of training when at least some recurrent terms of the network derivatives can be non-zero.

AB - Illustrated in this paper are the scientific trends of the early work in recurrent neural networks and the mathematics of training when at least some recurrent terms of the network derivatives can be non-zero.

UR - http://www.scopus.com/inward/record.url?scp=0028392260&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028392260&partnerID=8YFLogxK

U2 - 10.1109/tnn.1994.8753425

DO - 10.1109/tnn.1994.8753425

M3 - Article

AN - SCOPUS:0028392260

SN - 1045-9227

VL - 5

SP - 153

EP - 156

JO - IEEE Transactions on Neural Networks

JF - IEEE Transactions on Neural Networks

IS - 2

ER -

Dynamic recurrent neural networks: theory and applications

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Cite this