On-line learning in neural networks

David Saad (Editor)

Research output: Book/ReportBook

Abstract

On-line learning is one of the most powerful and commonly used techniques for training large layered networks and has been used successfully in many real-world applications. Traditional analytical methods have been recently complemented by ones from statistical physics and Bayesian statistics. This powerful combination of analytical methods provides more insight and deeper understanding of existing algorithms and leads to novel and principled proposals for their improvement. This book presents a coherent picture of the state-of-the-art in the theoretical analysis of on-line learning. An introduction relates the subject to other developments in neural networks and explains the overall picture. Surveys by leading experts in the field combine new and established material and enable non-experts to learn more about the techniques and methods used. This book, the first in the area, provides a comprehensive view of the subject and will be welcomed by mathematicians, scientists and engineers, whether in industry or academia.
Original languageEnglish
Place of PublicationCambridge
PublisherCambridge University Press
Number of pages408
Volume17
ISBN (Print)0262194163
DOIs
Publication statusPublished - Jan 1999

Publication series

NamePublications of the Newton Institute
PublisherCambridge University Press

Fingerprint

Physics
Statistics
Neural networks
Engineers
Industry

Keywords

  • On-line learning
  • training large layered networks

Cite this

Saad, D. (Ed.) (1999). On-line learning in neural networks. (Publications of the Newton Institute). Cambridge: Cambridge University Press. https://doi.org/10.2277/0521652634
Saad, David (Editor). / On-line learning in neural networks. Cambridge : Cambridge University Press, 1999. 408 p. (Publications of the Newton Institute).
@book{46912b261dc94e3a94aaaa946c6c8787,
title = "On-line learning in neural networks",
abstract = "On-line learning is one of the most powerful and commonly used techniques for training large layered networks and has been used successfully in many real-world applications. Traditional analytical methods have been recently complemented by ones from statistical physics and Bayesian statistics. This powerful combination of analytical methods provides more insight and deeper understanding of existing algorithms and leads to novel and principled proposals for their improvement. This book presents a coherent picture of the state-of-the-art in the theoretical analysis of on-line learning. An introduction relates the subject to other developments in neural networks and explains the overall picture. Surveys by leading experts in the field combine new and established material and enable non-experts to learn more about the techniques and methods used. This book, the first in the area, provides a comprehensive view of the subject and will be welcomed by mathematicians, scientists and engineers, whether in industry or academia.",
keywords = "On-line learning, training large layered networks",
editor = "David Saad",
year = "1999",
month = "1",
doi = "10.2277/0521652634",
language = "English",
isbn = "0262194163",
volume = "17",
series = "Publications of the Newton Institute",
publisher = "Cambridge University Press",
address = "United Kingdom",

}

Saad, D (ed.) 1999, On-line learning in neural networks. Publications of the Newton Institute, vol. 17, Cambridge University Press, Cambridge. https://doi.org/10.2277/0521652634

On-line learning in neural networks. / Saad, David (Editor).

Cambridge : Cambridge University Press, 1999. 408 p. (Publications of the Newton Institute).

Research output: Book/ReportBook

TY - BOOK

T1 - On-line learning in neural networks

A2 - Saad, David

PY - 1999/1

Y1 - 1999/1

N2 - On-line learning is one of the most powerful and commonly used techniques for training large layered networks and has been used successfully in many real-world applications. Traditional analytical methods have been recently complemented by ones from statistical physics and Bayesian statistics. This powerful combination of analytical methods provides more insight and deeper understanding of existing algorithms and leads to novel and principled proposals for their improvement. This book presents a coherent picture of the state-of-the-art in the theoretical analysis of on-line learning. An introduction relates the subject to other developments in neural networks and explains the overall picture. Surveys by leading experts in the field combine new and established material and enable non-experts to learn more about the techniques and methods used. This book, the first in the area, provides a comprehensive view of the subject and will be welcomed by mathematicians, scientists and engineers, whether in industry or academia.

AB - On-line learning is one of the most powerful and commonly used techniques for training large layered networks and has been used successfully in many real-world applications. Traditional analytical methods have been recently complemented by ones from statistical physics and Bayesian statistics. This powerful combination of analytical methods provides more insight and deeper understanding of existing algorithms and leads to novel and principled proposals for their improvement. This book presents a coherent picture of the state-of-the-art in the theoretical analysis of on-line learning. An introduction relates the subject to other developments in neural networks and explains the overall picture. Surveys by leading experts in the field combine new and established material and enable non-experts to learn more about the techniques and methods used. This book, the first in the area, provides a comprehensive view of the subject and will be welcomed by mathematicians, scientists and engineers, whether in industry or academia.

KW - On-line learning

KW - training large layered networks

UR - http://www.cambridge.org/uk/catalogue/catalogue.asp?isbn=0521652634

U2 - 10.2277/0521652634

DO - 10.2277/0521652634

M3 - Book

SN - 0262194163

VL - 17

T3 - Publications of the Newton Institute

BT - On-line learning in neural networks

PB - Cambridge University Press

CY - Cambridge

ER -

Saad D, (ed.). On-line learning in neural networks. Cambridge: Cambridge University Press, 1999. 408 p. (Publications of the Newton Institute). https://doi.org/10.2277/0521652634