Learning behavior and temporary minima of two-layer neural networks

Anne J. Annema; Klaas Hoen; Hans Wallinga

doi:10.1016/0893-6080(94)90087-6

Learning behavior and temporary minima of two-layer neural networks

Anne J. Annema
, Klaas Hoen
, Hans Wallinga

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

5 Citations (Scopus)

304 Downloads (Pure)

Abstract

This paper presents a mathematical analysis of the occurrence of temporary minima during training of a single-output, two-layer neural network, with learning according to the back-propagation algorithm. A new vector decomposition method is introduced, which simplifies the mathematical analysis of learning of neural networks considerably. The analysis shows that temporary minima are inherent to multilayer networks learning. A number of numerical results illustrate the analytical conclusions.

Original language	English
Pages (from-to)	1387-1403
Journal	Neural networks
Volume	7
Issue number	9
DOIs	https://doi.org/10.1016/0893-6080(94)90087-6
Publication status	Published - 1994

Keywords

Temporary minimum
Pattern classification
Learning
Neural networks
Multilayer perceptron
Back propagation

Access to Document

10.1016/0893-6080(94)90087-6

ArticleFinal published version, 1.76 MB

Cite this

@article{f47958519bd146e38217eec901a01472,

title = "Learning behavior and temporary minima of two-layer neural networks",

abstract = "This paper presents a mathematical analysis of the occurrence of temporary minima during training of a single-output, two-layer neural network, with learning according to the back-propagation algorithm. A new vector decomposition method is introduced, which simplifies the mathematical analysis of learning of neural networks considerably. The analysis shows that temporary minima are inherent to multilayer networks learning. A number of numerical results illustrate the analytical conclusions.",

keywords = "Temporary minimum, Pattern classification, Learning, Neural networks, Multilayer perceptron, Back propagation",

author = "Annema, \{Anne J.\} and Klaas Hoen and Hans Wallinga",

year = "1994",

doi = "10.1016/0893-6080(94)90087-6",

language = "English",

volume = "7",

pages = "1387--1403",

journal = "Neural networks",

issn = "0893-6080",

publisher = "Elsevier",

number = "9",

}

TY - JOUR

T1 - Learning behavior and temporary minima of two-layer neural networks

AU - Annema, Anne J.

AU - Hoen, Klaas

AU - Wallinga, Hans

PY - 1994

Y1 - 1994

N2 - This paper presents a mathematical analysis of the occurrence of temporary minima during training of a single-output, two-layer neural network, with learning according to the back-propagation algorithm. A new vector decomposition method is introduced, which simplifies the mathematical analysis of learning of neural networks considerably. The analysis shows that temporary minima are inherent to multilayer networks learning. A number of numerical results illustrate the analytical conclusions.

AB - This paper presents a mathematical analysis of the occurrence of temporary minima during training of a single-output, two-layer neural network, with learning according to the back-propagation algorithm. A new vector decomposition method is introduced, which simplifies the mathematical analysis of learning of neural networks considerably. The analysis shows that temporary minima are inherent to multilayer networks learning. A number of numerical results illustrate the analytical conclusions.

KW - Temporary minimum

KW - Pattern classification

KW - Learning

KW - Neural networks

KW - Multilayer perceptron

KW - Back propagation

U2 - 10.1016/0893-6080(94)90087-6

DO - 10.1016/0893-6080(94)90087-6

M3 - Article

SN - 0893-6080

VL - 7

SP - 1387

EP - 1403

JO - Neural networks

JF - Neural networks

IS - 9

ER -

Learning behavior and temporary minima of two-layer neural networks

Abstract

Keywords

Access to Document

Fingerprint

Cite this