Extracting fuzzy symbolic representation from artificial neural networks

Maciej Faifer; Cezary Janikow; Krzysztof Krawiec

doi:10.1109/NAFIPS.1999.781764

Extracting fuzzy symbolic representation from artificial neural networks

Maciej Faifer, Cezary Janikow, Krzysztof Krawiec

University of Missouri-St. Louis

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

Abstract

The paper presents FUZZYTREPAN, a pedagogical approach to the problem of extracting comprehensible symbolic knowledge from trained artificial neural networks. This approach extends the previously proposed TREPAN method in two ways: it uses fuzzy representation in its knowledge extraction process (by means of fuzzy decision trees), and it uses additional heuristics in its process of generating artificial data. The paper describes the proposed approach in detail, and it presents its empirical evaluation on popular machine learning benchmarks

Original language	American English
Journal	North American Fuzzy Information Processing Society
DOIs	https://doi.org/10.1109/NAFIPS.1999.781764
State	Published - Jan 1 1999

Disciplines

Computer Sciences
Artificial Intelligence and Robotics

Access to Document

10.1109/NAFIPS.1999.781764License: Unspecified

Cite this

@article{b7af9e5350ef44f499ad5e8ea7790d32,

title = "Extracting fuzzy symbolic representation from artificial neural networks",

abstract = " The paper presents FUZZYTREPAN, a pedagogical approach to the problem of extracting comprehensible symbolic knowledge from trained artificial neural networks. This approach extends the previously proposed TREPAN method in two ways: it uses fuzzy representation in its knowledge extraction process (by means of fuzzy decision trees), and it uses additional heuristics in its process of generating artificial data. The paper describes the proposed approach in detail, and it presents its empirical evaluation on popular machine learning benchmarks ",

author = "Maciej Faifer and Cezary Janikow and Krzysztof Krawiec",

year = "1999",

month = jan,

day = "1",

doi = "10.1109/NAFIPS.1999.781764",

language = "American English",

journal = "North American Fuzzy Information Processing Society",

}

TY - JOUR

T1 - Extracting fuzzy symbolic representation from artificial neural networks

AU - Faifer, Maciej

AU - Janikow, Cezary

AU - Krawiec, Krzysztof

PY - 1999/1/1

Y1 - 1999/1/1

N2 - The paper presents FUZZYTREPAN, a pedagogical approach to the problem of extracting comprehensible symbolic knowledge from trained artificial neural networks. This approach extends the previously proposed TREPAN method in two ways: it uses fuzzy representation in its knowledge extraction process (by means of fuzzy decision trees), and it uses additional heuristics in its process of generating artificial data. The paper describes the proposed approach in detail, and it presents its empirical evaluation on popular machine learning benchmarks

AB - The paper presents FUZZYTREPAN, a pedagogical approach to the problem of extracting comprehensible symbolic knowledge from trained artificial neural networks. This approach extends the previously proposed TREPAN method in two ways: it uses fuzzy representation in its knowledge extraction process (by means of fuzzy decision trees), and it uses additional heuristics in its process of generating artificial data. The paper describes the proposed approach in detail, and it presents its empirical evaluation on popular machine learning benchmarks

UR - https://www.researchgate.net/profile/Krzysztof_Krawiec2/publication/3809013_Extracting_Fuzzy_Symbolic_Representation_from_Artificial_Neural_Networks/links/0046351e24f40492d2000000.pdf

U2 - 10.1109/NAFIPS.1999.781764

DO - 10.1109/NAFIPS.1999.781764

M3 - Article

JO - North American Fuzzy Information Processing Society

JF - North American Fuzzy Information Processing Society

ER -

Extracting fuzzy symbolic representation from artificial neural networks

Abstract

Disciplines

Access to Document

Other files and links

Cite this