Extracting Knowledge From Neural Networks

Christie M. Fuller; Rick L. Wilson

doi:10.4018/978-1-59904-933-5.ch062

Extracting Knowledge From Neural Networks

Christie M. Fuller, Rick L. Wilson

Oklahoma State University

Research output: Chapter in Book/Report/Conference proceeding › Chapter

Abstract

Neural networks (NN) as classifier systems have shown great promise in many problem domains in empirical studies over the past two decades. Using case classification accuracy as the criteria, neural networks have typically outperformed traditional parametric techniques (e.g., discriminant analysis, logistic regression) as well as other non-parametric approaches (e.g., various inductive learning systems such as ID3, C4.5, CART, etc.).

Original language	American English
Title of host publication	Knowledge Management: Concepts, Methodologies, Tools and Applications
DOIs	https://doi.org/10.4018/978-1-59904-933-5.ch062
State	Published - 2008
Externally published	Yes

EGS Disciplines

Operations and Supply Chain Management

Access to Document

10.4018/978-1-59904-933-5.ch062License: Unspecified

Cite this

@inbook{bddd7d18c6c14560bf4e57fe0873a6f2,

title = "Extracting Knowledge From Neural Networks",

abstract = " Neural networks (NN) as classifier systems have shown great promise in many problem domains in empirical studies over the past two decades. Using case classification accuracy as the criteria, neural networks have typically outperformed traditional parametric techniques (e.g., discriminant analysis, logistic regression) as well as other non-parametric approaches (e.g., various inductive learning systems such as ID3, C4.5, CART, etc.).",

author = "Fuller, {Christie M.} and Wilson, {Rick L.}",

note = "Neural networks (NN) as classifier systems have shown great promise in many problem domains in empirical studies over the past two decades. Using case classification accuracy as the criteria, neural networks have typically outperformed traditional parametric techniques (e.g., discriminant analysis, logistic regression) as well as other non-parametric approaches (e.g., various inductive learning systems such as ID3, C4.5, CART, etc.).",

year = "2008",

doi = "10.4018/978-1-59904-933-5.ch062",

language = "American English",

booktitle = "Knowledge Management: Concepts, Methodologies, Tools and Applications",

}

TY - CHAP

T1 - Extracting Knowledge From Neural Networks

AU - Fuller, Christie M.

AU - Wilson, Rick L.

N1 - Neural networks (NN) as classifier systems have shown great promise in many problem domains in empirical studies over the past two decades. Using case classification accuracy as the criteria, neural networks have typically outperformed traditional parametric techniques (e.g., discriminant analysis, logistic regression) as well as other non-parametric approaches (e.g., various inductive learning systems such as ID3, C4.5, CART, etc.).

PY - 2008

Y1 - 2008

N2 - Neural networks (NN) as classifier systems have shown great promise in many problem domains in empirical studies over the past two decades. Using case classification accuracy as the criteria, neural networks have typically outperformed traditional parametric techniques (e.g., discriminant analysis, logistic regression) as well as other non-parametric approaches (e.g., various inductive learning systems such as ID3, C4.5, CART, etc.).

AB - Neural networks (NN) as classifier systems have shown great promise in many problem domains in empirical studies over the past two decades. Using case classification accuracy as the criteria, neural networks have typically outperformed traditional parametric techniques (e.g., discriminant analysis, logistic regression) as well as other non-parametric approaches (e.g., various inductive learning systems such as ID3, C4.5, CART, etc.).

UR - http://dx.doi.org/10.4018/978-1-59904-933-5.ch062

U2 - 10.4018/978-1-59904-933-5.ch062

DO - 10.4018/978-1-59904-933-5.ch062

M3 - Chapter

BT - Knowledge Management: Concepts, Methodologies, Tools and Applications

ER -

Extracting Knowledge From Neural Networks

Abstract

EGS Disciplines

Access to Document

Other files and links

Fingerprint

Cite this