Interpretation of artificial neural networks by means of fuzzy rules

被引：83
|
作者：
Castro, JL [1 ]
Mantas, CJ [1 ]
Benítez, JM [1 ]
机构：
[1] Univ Granada, Dept Comp Sci & Artificial Intelligence, E-18071 Granada, Spain
来源：
IEEE TRANSACTIONS ON NEURAL NETWORKS | 2002年 / 13卷 / 01期
关键词：
artificial neural networks (ANNs); extraction; fuzzy rules; interpretation;
D O I：
10.1109/72.977279
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper presents an extension of the method presented by Benitez et al. for extracting fuzzy rules from an artificial neural network (ANN) that express exactly its behavior. The extraction process provides an interpretation of the ANN in terms of fuzzy rules. The fuzzy rules presented in this paper are in accordance with the domain of the input variables. These rules use a new operator in the antecedent. The properties and the intuitive meaning of this operator are studied. Next, the role of the biases in the fuzzy rule-based systems is analyzed. Several examples are presented to comment on the obtained fuzzy rule-based systems. Finally, the interpretation of ANNs with two or more hidden layers is also studied.
引用
收藏
页码：101 / 116
页数：16
相关论文
共 50 条
  • [31] Abstracting rules with fuzzy neural networks and fuzzy control of product development
    Tsinghua Univ, Beijing, China
    Qinghua Daxue Xuebao, 7 (33-36):
  • [32] Extraction of Symbolic Rules from Artificial Neural Networks
    Kamruzzaman, S. M.
    Islam, Md. Monirul
    PROCEEDINGS OF WORLD ACADEMY OF SCIENCE, ENGINEERING AND TECHNOLOGY, VOL 10, 2005, 10 : 271 - 277
  • [33] Uncertainty of Rules Extracted from Artificial Neural Networks
    Lee, Hurnjoo
    Kim, Hyeoncheol
    APPLIED ARTIFICIAL INTELLIGENCE, 2021, 35 (08) : 589 - 604
  • [34] Extracting DNF rules from artificial neural networks
    Viktor, HL
    Cloete, I
    FROM NATURAL TO ARTIFICIAL NEURAL COMPUTATION, 1995, 930 : 611 - 618
  • [35] Genetically optimized hybrid Fuzzy Neural Networks with the aid of TSK fuzzy inference rules and Polynomial Neural Networks
    Oh, SK
    Pedryez, W
    Kim, HK
    Kim, YK
    COMPUTATIONAL INTELLIGENCE AND BIOINSPIRED SYSTEMS, PROCEEDINGS, 2005, 3512 : 407 - 415
  • [36] Artificial Neural Networks and Fuzzy Neural Networks for Solving Civil Engineering Problems
    Knezevic, Milos
    Cvetkovska, Meri
    Hanak, Tomas
    Braganca, Luis
    Soltesz, Andrej
    COMPLEXITY, 2018,
  • [37] INTERPRETATION OF INFRARED-SPECTRA BY ARTIFICIAL NEURAL NETWORKS
    MEYER, M
    WEIGELT, T
    ANALYTICA CHIMICA ACTA, 1992, 265 (02) : 183 - 190
  • [38] Interpretation of captopril renography using artificial neural networks
    Nielsen, M
    Granerus, G
    Ohlsson, M
    Holst, H
    Thorsson, O
    Edenbrandt, L
    CLINICAL PHYSIOLOGY AND FUNCTIONAL IMAGING, 2005, 25 (05) : 293 - 296
  • [39] Analysis and interpretation of Stokes profiles with artificial neural networks
    Carroll, TA
    Staude, J
    SOLAR ENCOUNTER, 2001, 493 : 183 - 188
  • [40] Artificial neural networks and image interpretation: A ghost in the machine
    Scott, JA
    SEMINARS IN ULTRASOUND CT AND MRI, 2004, 25 (05) : 396 - 403
12345