Knowledge extraction from a class of support vector machines using the fuzzy all-permutations rule-base

Shahaf Duenyas; Michael Margaliot

doi:10.1109/CCMB.2011.5952107

Knowledge extraction from a class of support vector machines using the fuzzy all-permutations rule-base

Shahaf Duenyas^*, Michael Margaliot

^*Corresponding author for this work

School of Electrical Engineering

Tel Aviv University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

Support vector machines (SVMs) proved to be highly efficient in various classification tasks. However, the knowledge learned by the SVM is encoded in a long list of parameter values and it is not easy to comprehend what the SVM is actually computing. We show that certain types of SVMs are mathematically equivalent to a specific fuzzy rule base, the fuzzy all permutations rule base (FARB). This equivalence can be used to provide a symbolic representation of the SVM functioning. This leads to a new approach for knowledge extraction from SVMs. Two simple examples demonstrate the effectiveness of this approach.

Original language	English
Title of host publication	IEEE SSCI 2011 - Symposium Series on Computational Intelligence - CCMB 2011
Subtitle of host publication	2011 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain
Pages	59-65
Number of pages	7
DOIs	https://doi.org/10.1109/CCMB.2011.5952107
State	Published - 2011
Event	Symposium Series on Computational Intelligence, IEEE SSCI 2011 - 2011 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2011 - Paris, France Duration: 11 Apr 2011 → 15 Apr 2011

Publication series

Name	IEEE SSCI 2011 - Symposium Series on Computational Intelligence - CCMB 2011: 2011 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain

Conference

Conference	Symposium Series on Computational Intelligence, IEEE SSCI 2011 - 2011 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2011
Country/Territory	France
City	Paris
Period	11/04/11 → 15/04/11

Access to Document

10.1109/CCMB.2011.5952107

Cite this

Duenyas, S., & Margaliot, M. (2011). Knowledge extraction from a class of support vector machines using the fuzzy all-permutations rule-base. In IEEE SSCI 2011 - Symposium Series on Computational Intelligence - CCMB 2011: 2011 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (pp. 59-65). Article 5952107 (IEEE SSCI 2011 - Symposium Series on Computational Intelligence - CCMB 2011: 2011 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain). https://doi.org/10.1109/CCMB.2011.5952107

Duenyas, Shahaf ; Margaliot, Michael. / Knowledge extraction from a class of support vector machines using the fuzzy all-permutations rule-base. IEEE SSCI 2011 - Symposium Series on Computational Intelligence - CCMB 2011: 2011 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain. 2011. pp. 59-65 (IEEE SSCI 2011 - Symposium Series on Computational Intelligence - CCMB 2011: 2011 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain).

@inproceedings{90f2276f515c40a09d8960b1b43d8f7e,

title = "Knowledge extraction from a class of support vector machines using the fuzzy all-permutations rule-base",

abstract = "Support vector machines (SVMs) proved to be highly efficient in various classification tasks. However, the knowledge learned by the SVM is encoded in a long list of parameter values and it is not easy to comprehend what the SVM is actually computing. We show that certain types of SVMs are mathematically equivalent to a specific fuzzy rule base, the fuzzy all permutations rule base (FARB). This equivalence can be used to provide a symbolic representation of the SVM functioning. This leads to a new approach for knowledge extraction from SVMs. Two simple examples demonstrate the effectiveness of this approach.",

author = "Shahaf Duenyas and Michael Margaliot",

year = "2011",

doi = "10.1109/CCMB.2011.5952107",

language = "אנגלית",

isbn = "9781424498918",

series = "IEEE SSCI 2011 - Symposium Series on Computational Intelligence - CCMB 2011: 2011 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain",

pages = "59--65",

booktitle = "IEEE SSCI 2011 - Symposium Series on Computational Intelligence - CCMB 2011",

note = "Symposium Series on Computational Intelligence, IEEE SSCI 2011 - 2011 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2011 ; Conference date: 11-04-2011 Through 15-04-2011",

}

Duenyas, S & Margaliot, M 2011, Knowledge extraction from a class of support vector machines using the fuzzy all-permutations rule-base. in IEEE SSCI 2011 - Symposium Series on Computational Intelligence - CCMB 2011: 2011 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain., 5952107, IEEE SSCI 2011 - Symposium Series on Computational Intelligence - CCMB 2011: 2011 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, pp. 59-65, Symposium Series on Computational Intelligence, IEEE SSCI 2011 - 2011 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2011, Paris, France, 11/04/11. https://doi.org/10.1109/CCMB.2011.5952107

Knowledge extraction from a class of support vector machines using the fuzzy all-permutations rule-base. / Duenyas, Shahaf; Margaliot, Michael.
IEEE SSCI 2011 - Symposium Series on Computational Intelligence - CCMB 2011: 2011 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain. 2011. p. 59-65 5952107 (IEEE SSCI 2011 - Symposium Series on Computational Intelligence - CCMB 2011: 2011 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Knowledge extraction from a class of support vector machines using the fuzzy all-permutations rule-base

AU - Duenyas, Shahaf

AU - Margaliot, Michael

PY - 2011

Y1 - 2011

N2 - Support vector machines (SVMs) proved to be highly efficient in various classification tasks. However, the knowledge learned by the SVM is encoded in a long list of parameter values and it is not easy to comprehend what the SVM is actually computing. We show that certain types of SVMs are mathematically equivalent to a specific fuzzy rule base, the fuzzy all permutations rule base (FARB). This equivalence can be used to provide a symbolic representation of the SVM functioning. This leads to a new approach for knowledge extraction from SVMs. Two simple examples demonstrate the effectiveness of this approach.

AB - Support vector machines (SVMs) proved to be highly efficient in various classification tasks. However, the knowledge learned by the SVM is encoded in a long list of parameter values and it is not easy to comprehend what the SVM is actually computing. We show that certain types of SVMs are mathematically equivalent to a specific fuzzy rule base, the fuzzy all permutations rule base (FARB). This equivalence can be used to provide a symbolic representation of the SVM functioning. This leads to a new approach for knowledge extraction from SVMs. Two simple examples demonstrate the effectiveness of this approach.

UR - http://www.scopus.com/inward/record.url?scp=79961158369&partnerID=8YFLogxK

U2 - 10.1109/CCMB.2011.5952107

DO - 10.1109/CCMB.2011.5952107

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:79961158369

SN - 9781424498918

T3 - IEEE SSCI 2011 - Symposium Series on Computational Intelligence - CCMB 2011: 2011 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain

SP - 59

EP - 65

BT - IEEE SSCI 2011 - Symposium Series on Computational Intelligence - CCMB 2011

T2 - Symposium Series on Computational Intelligence, IEEE SSCI 2011 - 2011 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2011

Y2 - 11 April 2011 through 15 April 2011

ER -

Duenyas S, Margaliot M. Knowledge extraction from a class of support vector machines using the fuzzy all-permutations rule-base. In IEEE SSCI 2011 - Symposium Series on Computational Intelligence - CCMB 2011: 2011 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain. 2011. p. 59-65. 5952107. (IEEE SSCI 2011 - Symposium Series on Computational Intelligence - CCMB 2011: 2011 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain). doi: 10.1109/CCMB.2011.5952107

Knowledge extraction from a class of support vector machines using the fuzzy all-permutations rule-base

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this