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

被引：15

作者：

Kolman, Eyal ^{[1
]}

Margaliot, Michael ^{[1
]}

机构：

[1] Tel Aviv Univ, Sch Elect Engn Syst, IL-69978 Tel Aviv, Israel

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 2007年 / 18卷 / 03期

关键词：

feedforward neural networks; hybrid intelligent systems; knowledge extraction; neurofuzzy systems; rule extraction; rule generation;

D O I：

10.1109/TNN.2007.891686

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A major drawback of artificial neural networks (ANNs) is their black-box character. Even when the trained network performs adequately, it is very difficult to understand its operation. In this letter, we use the mathematical equivalence between ANNs 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 light emitting diode (LED) device. The method provides a symbolic and comprehensible description of the knowledge learned by the network during its training.

引用

页码：925 / 931

页数：7

共 49 条

[1] Knowledge extraction from neural networks using the all-permutations fuzzy rule base: The LED display recognition problem
Kolman, E
Margaliot, M
COMPUTATIONAL INTELLIGENCE AND BIOINSPIRED SYSTEMS, PROCEEDINGS, 2005, 3512 : 1222 - 1229
[2] Neural network rule extraction and the LED display recognition problem
Setiono, Rudy
Tanaka, Masahiro
22ND INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI 2010), PROCEEDINGS, VOL 2, 2010, : 53 - 56
[3] Rule extraction from neural networks using fuzzy sets
Wettayaprasit, W
Lursinsap, C
Chu, CHH
ICONIP'02: PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING: COMPUTATIONAL INTELLIGENCE FOR THE E-AGE, 2002, : 2582 - 2586
[4] Knowledge extraction from scenery images and the recognition using Fuzzy Inference Neural Networks
Iyatomi, H
Hagiwara, M
1998 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS, VOLS 1-5, 1998, : 4486 - 4491
[5] Knowledge extraction from scenery images and recognition using fuzzy inference neural networks
Iyatomi, H
Hagiwara, M
ELECTRONICS AND COMMUNICATIONS IN JAPAN PART II-ELECTRONICS, 2003, 86 (03): : 82 - 90
[6] DENAS Automated Rule Generation by Knowledge Extraction from Neural Networks
Chen, Simin
Bateni, Soroush
Grandhi, Sampath
Li, Xiaodi
Liu, Cong
Yang, Wei
PROCEEDINGS OF THE 28TH ACM JOINT MEETING ON EUROPEAN SOFTWARE ENGINEERING CONFERENCE AND SYMPOSIUM ON THE FOUNDATIONS OF SOFTWARE ENGINEERING (ESEC/FSE '20), 2020, : 813 - 825
[7] Decision Making Problem Solving using Fuzzy Networks with Rule Base Aggregation
Yaakob, Abdul Malek
Gegov, Alexander
Rahman, Siti Fatimah Abdul
2017 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS (FUZZ-IEEE), 2017,
[8] A new approach to weighted fuzzy production rule extraction from neural networks
Fan, TG
Wang, XZ
PROCEEDINGS OF THE 2004 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7, 2004, : 3348 - 3351
[9] Fuzzy DIFACONN-miner: A novel approach for fuzzy rule extraction from neural networks
Kulluk, Sinem
Ozbakir, Lale
Baykasoglu, Adil
EXPERT SYSTEMS WITH APPLICATIONS, 2013, 40 (03) : 938 - 946
[10] Beyond simple rule extraction: Acquiring planning knowledge from neural networks
Sun, R
Peterson, T
Sessions, C
NEURAL NETS WIRN VIETRI-01, 2002, : 288 - 300

← 1 2 3 4 5 →