Effect of time correlation of input patterns on the convergence of on-line learning

Tsuyoshi Hondou; Mitsuaki Yamamoto; Yasuji Sawada; Yoshihiro Hayakawa

doi:10.1103/PhysRevE.53.4217

Effect of time correlation of input patterns on the convergence of on-line learning

Tsuyoshi Hondou, Mitsuaki Yamamoto, Yasuji Sawada, Yoshihiro Hayakawa

SCI - Research and Education Support

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

3 Citations (Scopus)

Abstract

We studied the effects of time correlation of subsequent patterns on the convergence of on-line learning by a feedforward neural network with the backpropagation algorithm. By using a chaotic time series as sequences of correlated patterns, we found that the unexpected scaling of converging time with the learning parameter emerges when time-correlated patterns accelerate the learning process.

Original language	English
Pages (from-to)	4217-4220
Number of pages	4
Journal	Physical Review E - Statistical Physics, Plasmas, Fluids, and Related Interdisciplinary Topics
Volume	53
Issue number	4
DOIs	https://doi.org/10.1103/PhysRevE.53.4217
Publication status	Published - 1996

ASJC Scopus subject areas

Statistical and Nonlinear Physics
Statistics and Probability
Condensed Matter Physics

Access to Document

10.1103/PhysRevE.53.4217

Fingerprint Dive into the research topics of 'Effect of time correlation of input patterns on the convergence of on-line learning'. Together they form a unique fingerprint.

Cite this

@article{6b31fe5c5be94045a5a37951834c54b4,

title = "Effect of time correlation of input patterns on the convergence of on-line learning",

abstract = "We studied the effects of time correlation of subsequent patterns on the convergence of on-line learning by a feedforward neural network with the backpropagation algorithm. By using a chaotic time series as sequences of correlated patterns, we found that the unexpected scaling of converging time with the learning parameter emerges when time-correlated patterns accelerate the learning process.",

author = "Tsuyoshi Hondou and Mitsuaki Yamamoto and Yasuji Sawada and Yoshihiro Hayakawa",

year = "1996",

doi = "10.1103/PhysRevE.53.4217",

language = "English",

volume = "53",

pages = "4217--4220",

journal = "Physical Review E",

issn = "2470-0045",

publisher = "American Physical Society",

number = "4",

}

TY - JOUR

T1 - Effect of time correlation of input patterns on the convergence of on-line learning

AU - Hondou, Tsuyoshi

AU - Yamamoto, Mitsuaki

AU - Sawada, Yasuji

AU - Hayakawa, Yoshihiro

PY - 1996

Y1 - 1996

N2 - We studied the effects of time correlation of subsequent patterns on the convergence of on-line learning by a feedforward neural network with the backpropagation algorithm. By using a chaotic time series as sequences of correlated patterns, we found that the unexpected scaling of converging time with the learning parameter emerges when time-correlated patterns accelerate the learning process.

AB - We studied the effects of time correlation of subsequent patterns on the convergence of on-line learning by a feedforward neural network with the backpropagation algorithm. By using a chaotic time series as sequences of correlated patterns, we found that the unexpected scaling of converging time with the learning parameter emerges when time-correlated patterns accelerate the learning process.

UR - http://www.scopus.com/inward/record.url?scp=0040389085&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0040389085&partnerID=8YFLogxK

U2 - 10.1103/PhysRevE.53.4217

DO - 10.1103/PhysRevE.53.4217

M3 - Article

AN - SCOPUS:0040389085

VL - 53

SP - 4217

EP - 4220

JO - Physical Review E

JF - Physical Review E

SN - 2470-0045

IS - 4

ER -

Effect of time correlation of input patterns on the convergence of on-line learning

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Cite this