Interpretation of Recurrent Neural Networks

Morten With Pedersen; Jan Larsen

doi:10.1109/NNSP.1997.622386

Interpretation of Recurrent Neural Networks

Morten With Pedersen, Jan Larsen

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

701 Downloads (Pure)

Abstract

This paper addresses techniques for interpretation and characterization of trained recurrent nets for time series problems. In particular, we focus on assessment of effective memory and suggest an operational definition of memory. Further we discuss the evaluation of learning curves. Various numerical experiments on time series prediction problems are used to illustrate the potential of the suggested methods

Original language	English
Title of host publication	Proceedings of the IEEE Workshop on Neural Networks for Signal Processing VII
Place of Publication	Piscataway, New Jersey
Publisher	IEEE
Publication date	1997
Pages	82-91
ISBN (Print)	0-7803-4256-9
DOIs	https://doi.org/10.1109/NNSP.1997.622386
Publication status	Published - 1997
Event	1997 IEEE Workshop on Neural Networks for Signal Processing VII - Amelia Island, United States Duration: 24 Sept 1997 → 26 Sept 1997 Conference number: 7 https://ieeexplore.ieee.org/xpl/conhome/4900/proceeding

Conference

Conference	1997 IEEE Workshop on Neural Networks for Signal Processing VII
Number	7
Country/Territory	United States
City	Amelia Island
Period	24/09/1997 → 26/09/1997
Internet address	https://ieeexplore.ieee.org/xpl/conhome/4900/proceeding

Bibliographical note

Copyright: 1997 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE

Access to Document

10.1109/NNSP.1997.622386

PedersenFinal published version, 622 KB

OpenUrl availability

Full text

Cite this

@inproceedings{754a0bbe1c654566b6d8ef1646bc146e,

title = "Interpretation of Recurrent Neural Networks",

abstract = "This paper addresses techniques for interpretation and characterization of trained recurrent nets for time series problems. In particular, we focus on assessment of effective memory and suggest an operational definition of memory. Further we discuss the evaluation of learning curves. Various numerical experiments on time series prediction problems are used to illustrate the potential of the suggested methods",

author = "Pedersen, {Morten With} and Jan Larsen",

note = "Copyright: 1997 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE; 1997 IEEE Workshop on Neural Networks for Signal Processing VII, NNSP 1997 ; Conference date: 24-09-1997 Through 26-09-1997",

year = "1997",

doi = "10.1109/NNSP.1997.622386",

language = "English",

isbn = "0-7803-4256-9",

pages = "82--91",

booktitle = "Proceedings of the IEEE Workshop on Neural Networks for Signal Processing VII",

publisher = "IEEE",

address = "United States",

url = "https://ieeexplore.ieee.org/xpl/conhome/4900/proceeding",

}

TY - GEN

T1 - Interpretation of Recurrent Neural Networks

AU - Pedersen, Morten With

AU - Larsen, Jan

N1 - Conference code: 7

PY - 1997

Y1 - 1997

N2 - This paper addresses techniques for interpretation and characterization of trained recurrent nets for time series problems. In particular, we focus on assessment of effective memory and suggest an operational definition of memory. Further we discuss the evaluation of learning curves. Various numerical experiments on time series prediction problems are used to illustrate the potential of the suggested methods

AB - This paper addresses techniques for interpretation and characterization of trained recurrent nets for time series problems. In particular, we focus on assessment of effective memory and suggest an operational definition of memory. Further we discuss the evaluation of learning curves. Various numerical experiments on time series prediction problems are used to illustrate the potential of the suggested methods

U2 - 10.1109/NNSP.1997.622386

DO - 10.1109/NNSP.1997.622386

M3 - Article in proceedings

SN - 0-7803-4256-9

SP - 82

EP - 91

BT - Proceedings of the IEEE Workshop on Neural Networks for Signal Processing VII

PB - IEEE

CY - Piscataway, New Jersey

T2 - 1997 IEEE Workshop on Neural Networks for Signal Processing VII

Y2 - 24 September 1997 through 26 September 1997

ER -

Interpretation of Recurrent Neural Networks

Abstract

Conference

Bibliographical note

Access to Document

OpenUrl availability

Fingerprint

Cite this