The learning dynamics of a universal approximator

Ansgar H. L. West; David Saad; Ian T. Nabney; Michael C. Mozer; Thomas Petsche; Michael I. Jordan

The learning dynamics of a universal approximator

Ansgar H. L. West
, David Saad
, Ian T. Nabney
, Michael C. Mozer
, Thomas Petsche
, Michael I. Jordan

Research output: Contribution to journal › Article (Academic Journal) › peer-review

3 Citations (Scopus)

14 Downloads (Pure)

Abstract

The learning properties of a universal approximator, a normalized committee machine with adjustable biases, are studied for on-line back-propagation learning. Within a statistical mechanics framework, numerical studies show that this model has features which do not exist in previously studied two-layer network models without adjustable biases, e.g., attractive suboptimal symmetric phases even for realizable cases and noiseless data.

Original language	English
Pages (from-to)	288-294
Number of pages	7
Journal	Advances in Neural Information Processing Systems
Volume	9
Publication status	Published - 1 May 1997

Bibliographical note

Copyright of the Massachusetts Institute of Technology Press (MIT Press)

Keywords

approximator, back-propagation, symmetric phases, realizable cases, noiseless data

Handle.net

Persistent link

Cite this

@article{fec7e38247aa43c1aa63afd6a519e18d,

title = "The learning dynamics of a universal approximator",

abstract = "The learning properties of a universal approximator, a normalized committee machine with adjustable biases, are studied for on-line back-propagation learning. Within a statistical mechanics framework, numerical studies show that this model has features which do not exist in previously studied two-layer network models without adjustable biases, e.g., attractive suboptimal symmetric phases even for realizable cases and noiseless data.",

keywords = "approximator, back-propagation, symmetric phases, realizable cases, noiseless data",

author = "West, \{Ansgar H. L.\} and David Saad and Nabney, \{Ian T.\} and Mozer, \{Michael C.\} and Thomas Petsche and Jordan, \{Michael I.\}",

note = "Copyright of the Massachusetts Institute of Technology Press (MIT Press)",

year = "1997",

month = may,

day = "1",

language = "English",

volume = "9",

pages = "288--294",

journal = "Advances in Neural Information Processing Systems",

issn = "1049-5258",

publisher = "Neural Information Processing Systems Foundation",

}

TY - JOUR

T1 - The learning dynamics of a universal approximator

AU - West, Ansgar H. L.

AU - Saad, David

AU - Nabney, Ian T.

AU - Mozer, Michael C.

AU - Petsche, Thomas

AU - Jordan, Michael I.

N1 - Copyright of the Massachusetts Institute of Technology Press (MIT Press)

PY - 1997/5/1

Y1 - 1997/5/1

N2 - The learning properties of a universal approximator, a normalized committee machine with adjustable biases, are studied for on-line back-propagation learning. Within a statistical mechanics framework, numerical studies show that this model has features which do not exist in previously studied two-layer network models without adjustable biases, e.g., attractive suboptimal symmetric phases even for realizable cases and noiseless data.

AB - The learning properties of a universal approximator, a normalized committee machine with adjustable biases, are studied for on-line back-propagation learning. Within a statistical mechanics framework, numerical studies show that this model has features which do not exist in previously studied two-layer network models without adjustable biases, e.g., attractive suboptimal symmetric phases even for realizable cases and noiseless data.

KW - approximator, back-propagation, symmetric phases, realizable cases, noiseless data

M3 - Article (Academic Journal)

SN - 1049-5258

VL - 9

SP - 288

EP - 294

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

ER -

The learning dynamics of a universal approximator

Abstract

Bibliographical note

Keywords

Handle.net

Fingerprint

Cite this