Adaptive on-line learning in changing environments

Noboru Murata, Klaus Robert Müller, Andreas Ziehe, Shun Ichi Amari

Research output: Chapter in Book/Report/Conference proceedingConference contribution

39 Citations (Scopus)

Abstract

An adaptive on-line algorithm extending the learning of learning idea is proposed and theoretically motivated. Relying only on gradient flow information it can be applied to learning continuous functions or distributions, even when no explicit loss function is given and the Hessian is not available. Its efficiency is demonstrated for a non-stationary blind separation task of acoustic signals.

Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems
PublisherNeural information processing systems foundation
Pages599-605
Number of pages7
ISBN (Print)0262100657, 9780262100656
Publication statusPublished - 1997
Externally publishedYes
Event10th Annual Conference on Neural Information Processing Systems, NIPS 1996 - Denver, CO
Duration: 1996 Dec 21996 Dec 5

Other

Other10th Annual Conference on Neural Information Processing Systems, NIPS 1996
CityDenver, CO
Period96/12/296/12/5

Fingerprint

Acoustics

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Murata, N., Müller, K. R., Ziehe, A., & Amari, S. I. (1997). Adaptive on-line learning in changing environments. In Advances in Neural Information Processing Systems (pp. 599-605). Neural information processing systems foundation.

Adaptive on-line learning in changing environments. / Murata, Noboru; Müller, Klaus Robert; Ziehe, Andreas; Amari, Shun Ichi.

Advances in Neural Information Processing Systems. Neural information processing systems foundation, 1997. p. 599-605.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Murata, N, Müller, KR, Ziehe, A & Amari, SI 1997, Adaptive on-line learning in changing environments. in Advances in Neural Information Processing Systems. Neural information processing systems foundation, pp. 599-605, 10th Annual Conference on Neural Information Processing Systems, NIPS 1996, Denver, CO, 96/12/2.
Murata N, Müller KR, Ziehe A, Amari SI. Adaptive on-line learning in changing environments. In Advances in Neural Information Processing Systems. Neural information processing systems foundation. 1997. p. 599-605
Murata, Noboru ; Müller, Klaus Robert ; Ziehe, Andreas ; Amari, Shun Ichi. / Adaptive on-line learning in changing environments. Advances in Neural Information Processing Systems. Neural information processing systems foundation, 1997. pp. 599-605
@inproceedings{7150237a61014a21867b2a57fb6dd4d5,
title = "Adaptive on-line learning in changing environments",
abstract = "An adaptive on-line algorithm extending the learning of learning idea is proposed and theoretically motivated. Relying only on gradient flow information it can be applied to learning continuous functions or distributions, even when no explicit loss function is given and the Hessian is not available. Its efficiency is demonstrated for a non-stationary blind separation task of acoustic signals.",
author = "Noboru Murata and M{\"u}ller, {Klaus Robert} and Andreas Ziehe and Amari, {Shun Ichi}",
year = "1997",
language = "English",
isbn = "0262100657",
pages = "599--605",
booktitle = "Advances in Neural Information Processing Systems",
publisher = "Neural information processing systems foundation",

}

TY - GEN

T1 - Adaptive on-line learning in changing environments

AU - Murata, Noboru

AU - Müller, Klaus Robert

AU - Ziehe, Andreas

AU - Amari, Shun Ichi

PY - 1997

Y1 - 1997

N2 - An adaptive on-line algorithm extending the learning of learning idea is proposed and theoretically motivated. Relying only on gradient flow information it can be applied to learning continuous functions or distributions, even when no explicit loss function is given and the Hessian is not available. Its efficiency is demonstrated for a non-stationary blind separation task of acoustic signals.

AB - An adaptive on-line algorithm extending the learning of learning idea is proposed and theoretically motivated. Relying only on gradient flow information it can be applied to learning continuous functions or distributions, even when no explicit loss function is given and the Hessian is not available. Its efficiency is demonstrated for a non-stationary blind separation task of acoustic signals.

UR - http://www.scopus.com/inward/record.url?scp=84898987101&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898987101&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84898987101

SN - 0262100657

SN - 9780262100656

SP - 599

EP - 605

BT - Advances in Neural Information Processing Systems

PB - Neural information processing systems foundation

ER -