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

[31] Bidirectional bridge between neural networks and linguistic knowledge: Linguistic rule extraction and learning from linguistic rules
Ishibuchi, H
Nii, M
Turksen, IB
1998 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS AT THE IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE - PROCEEDINGS, VOL 1-2, 1998, : 1112 - 1117
[32] THE EXTRACTION OF KNOWLEDGE RULES FROM ARTIFICIAL NEURAL NETWORKS APPLIED IN THE ELECTRIC LOAD DEMAND FORECAST PROBLEM
Steinmetz, Tarcisio R.
Cechin, Adelmo L.
Canto dos Santos, Jose V.
ICINCO 2009: PROCEEDINGS OF THE 6TH INTERNATIONAL CONFERENCE ON INFORMATICS IN CONTROL, AUTOMATION AND ROBOTICS, VOL 1: INTELLIGENT CONTROL SYSTEMS AND OPTIMIZATION, 2009, : 195 - 200
[33] Building an interpretable fuzzy rule base from data using orthogonal least squares - Application to a depollution problem
Destercke, Sebastien
Guillaume, Serge
Charnomordic, Brigitte
FUZZY SETS AND SYSTEMS, 2007, 158 (18) : 2078 - 2094
[34] Reduction of input vectors by using of attribute selection in rule extraction method from trained neural networks
Nii, M
Ogino, K
SICE 2003 ANNUAL CONFERENCE, VOLS 1-3, 2003, : 1576 - 1581
[35] Linguistic knowledge extraction from neural networks using maximum weight and frequency data representation
Wettayaprasit, Wiphada
Sangket, Unitsa
2006 IEEE CONFERENCE ON CYBERNETICS AND INTELLIGENT SYSTEMS, VOLS 1 AND 2, 2006, : 516 - +
[36] From knowledge discovery to implementation: A business intelligence approach using neural network rule extraction and decision tables
Mues, C
Baesens, B
Setiono, R
Vanthienen, J
PROFESSIONAL KNOWLEDGE MANAGEMENT, 2005, 3782 : 483 - 495
[37] Estimating Cloud Base Height From All-Sky Imagery Using Artificial Neural Networks
Borisov, M. A.
Krinitskiy, M. A.
Tilinina, N. D.
MOSCOW UNIVERSITY PHYSICS BULLETIN, 2023, 78 (SUPPL 1) : S85 - S95
[38] Estimating Cloud Base Height From All-Sky Imagery Using Artificial Neural Networks
M. A. Borisov
M. A. Krinitskiy
N. D. Tilinina
Moscow University Physics Bulletin, 2023, 78 : S85 - S95
[39] A Real Time Adaptive Resource Allocation Scheme for OFDM Systems Using GRBF-Neural Networks and Fuzzy Rule Base System
Rahman, Atta
Qureshi, Ijaz
Malik, Aqdas
Naseemi, Muhammad
INTERNATIONAL ARAB JOURNAL OF INFORMATION TECHNOLOGY, 2014, 11 (06) : 590 - 598
[40] Computer-Aided Heart Disease Diagnosis Using Recursive Rule Extraction Algorithms from Neural Networks
Chakraborty, Manomita
Biswas, Saroj Kumar
INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE AND APPLICATIONS, 2022, 21 (02)

← 1 2 3 4 5 →