Knowledge extraction from neural networks using the all-permutations fuzzy rule base: The LED display recognition problem

Eyal Kolman; Michael Margaliot

doi:10.1007/11494669_150

Knowledge extraction from neural networks using the all-permutations fuzzy rule base: The LED display recognition problem

Eyal Kolman, Michael Margaliot^*

^*Corresponding author for this work

School of Electrical Engineering

Tel Aviv University

Research output: Contribution to journal › Conference article › peer-review

1 Scopus citations

Abstract

A major drawback of artificial neural networks is their black-box character. In this paper, we use the equivalence between artificial neural networks and a specific fuzzy rule base to extract the knowledge embedded in the network. We demonstrate this using a benchmark problem: the recognition of digits produced by a LED device. The method provides a symbolic and comprehensible description of the knowledge learned by the network during its training.

Original language	English
Pages (from-to)	1222-1229
Number of pages	8
Journal	Lecture Notes in Computer Science
Volume	3512
DOIs	https://doi.org/10.1007/11494669_150
State	Published - 2005
Event	8th International Workshop on Artificial Neural Networks, IWANN 2005: Computational Intelligence and Bioinspired Systems - Vilanova i la Geltru, Spain Duration: 8 Jun 2005 → 10 Jun 2005

Access to Document

10.1007/11494669_150

Cite this

@article{dcadfc07b5674a01b6cc73e2c64437dc,

title = "Knowledge extraction from neural networks using the all-permutations fuzzy rule base: The LED display recognition problem",

abstract = "A major drawback of artificial neural networks is their black-box character. In this paper, we use the equivalence between artificial neural networks and a specific fuzzy rule base to extract the knowledge embedded in the network. We demonstrate this using a benchmark problem: the recognition of digits produced by a LED device. The method provides a symbolic and comprehensible description of the knowledge learned by the network during its training.",

author = "Eyal Kolman and Michael Margaliot",

year = "2005",

doi = "10.1007/11494669_150",

language = "אנגלית",

volume = "3512",

pages = "1222--1229",

journal = "Lecture Notes in Computer Science",

issn = "0302-9743",

publisher = "Springer Science and Business Media Deutschland GmbH",

note = "8th International Workshop on Artificial Neural Networks, IWANN 2005: Computational Intelligence and Bioinspired Systems ; Conference date: 08-06-2005 Through 10-06-2005",

}

TY - JOUR

T1 - Knowledge extraction from neural networks using the all-permutations fuzzy rule base

T2 - 8th International Workshop on Artificial Neural Networks, IWANN 2005: Computational Intelligence and Bioinspired Systems

AU - Kolman, Eyal

AU - Margaliot, Michael

PY - 2005

Y1 - 2005

N2 - A major drawback of artificial neural networks is their black-box character. In this paper, we use the equivalence between artificial neural networks and a specific fuzzy rule base to extract the knowledge embedded in the network. We demonstrate this using a benchmark problem: the recognition of digits produced by a LED device. The method provides a symbolic and comprehensible description of the knowledge learned by the network during its training.

AB - A major drawback of artificial neural networks is their black-box character. In this paper, we use the equivalence between artificial neural networks and a specific fuzzy rule base to extract the knowledge embedded in the network. We demonstrate this using a benchmark problem: the recognition of digits produced by a LED device. The method provides a symbolic and comprehensible description of the knowledge learned by the network during its training.

UR - http://www.scopus.com/inward/record.url?scp=25144511385&partnerID=8YFLogxK

U2 - 10.1007/11494669_150

DO - 10.1007/11494669_150

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.conferencearticle???

AN - SCOPUS:25144511385

SN - 0302-9743

VL - 3512

SP - 1222

EP - 1229

JO - Lecture Notes in Computer Science

JF - Lecture Notes in Computer Science

Y2 - 8 June 2005 through 10 June 2005

ER -

Knowledge extraction from neural networks using the all-permutations fuzzy rule base: The LED display recognition problem

Abstract

Access to Document

Other files and links

Fingerprint

Cite this