Designing neural network architectures for pattern recognition

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

An appropriately designed architecture of a neural network is essential to many realistic pattern-recognition tasks. A choice of just the right number of neurons, and their interconnections, can cut learning costs by orders of magnitude, and still warrant high classification accuracy. Surprisingly, textbooks often neglect this issue. A specialist seeking systematic information will soon realize that relevant material is scattered over diverse sources, each with a different perspective, terminology and goals. This brief survey attempts to rectify the situation by explaining the involved aspects, and by describing some of the fundamental techniques.

Original languageEnglish
Pages (from-to)151-170
Number of pages20
JournalKnowledge Engineering Review
Volume15
Issue number2
DOIs
StatePublished - Jun 1 2000
Externally publishedYes

Fingerprint

Textbooks
Terminology
Network architecture
Neurons
Pattern recognition
Neural networks
Costs

ASJC Scopus subject areas

  • Artificial Intelligence
  • Control and Systems Engineering

Cite this

Designing neural network architectures for pattern recognition. / Kubat, Miroslav.

In: Knowledge Engineering Review, Vol. 15, No. 2, 01.06.2000, p. 151-170.

Research output: Contribution to journalArticle

@article{18ed88d0f1c5464a8ea0dde2b313e2e0,
title = "Designing neural network architectures for pattern recognition",
abstract = "An appropriately designed architecture of a neural network is essential to many realistic pattern-recognition tasks. A choice of just the right number of neurons, and their interconnections, can cut learning costs by orders of magnitude, and still warrant high classification accuracy. Surprisingly, textbooks often neglect this issue. A specialist seeking systematic information will soon realize that relevant material is scattered over diverse sources, each with a different perspective, terminology and goals. This brief survey attempts to rectify the situation by explaining the involved aspects, and by describing some of the fundamental techniques.",
author = "Miroslav Kubat",
year = "2000",
month = "6",
day = "1",
doi = "10.1017/S0269888900002022",
language = "English",
volume = "15",
pages = "151--170",
journal = "Knowledge Engineering Review",
issn = "0269-8889",
publisher = "Cambridge University Press",
number = "2",

}

TY - JOUR

T1 - Designing neural network architectures for pattern recognition

AU - Kubat, Miroslav

PY - 2000/6/1

Y1 - 2000/6/1

N2 - An appropriately designed architecture of a neural network is essential to many realistic pattern-recognition tasks. A choice of just the right number of neurons, and their interconnections, can cut learning costs by orders of magnitude, and still warrant high classification accuracy. Surprisingly, textbooks often neglect this issue. A specialist seeking systematic information will soon realize that relevant material is scattered over diverse sources, each with a different perspective, terminology and goals. This brief survey attempts to rectify the situation by explaining the involved aspects, and by describing some of the fundamental techniques.

AB - An appropriately designed architecture of a neural network is essential to many realistic pattern-recognition tasks. A choice of just the right number of neurons, and their interconnections, can cut learning costs by orders of magnitude, and still warrant high classification accuracy. Surprisingly, textbooks often neglect this issue. A specialist seeking systematic information will soon realize that relevant material is scattered over diverse sources, each with a different perspective, terminology and goals. This brief survey attempts to rectify the situation by explaining the involved aspects, and by describing some of the fundamental techniques.

UR - http://www.scopus.com/inward/record.url?scp=0034205581&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034205581&partnerID=8YFLogxK

U2 - 10.1017/S0269888900002022

DO - 10.1017/S0269888900002022

M3 - Article

AN - SCOPUS:0034205581

VL - 15

SP - 151

EP - 170

JO - Knowledge Engineering Review

JF - Knowledge Engineering Review

SN - 0269-8889

IS - 2

ER -