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
  • [1] An Extension of the Method for Fuzzy Rules Extraction by Means of Artificial Neural Networks
    Gorecki, Jan
    Sperka, Roman
    Spisak, Marek
    INTELLIGENT DECISION TECHNOLOGIES, 2013, 255 : 65 - 73
  • [2] Interpretation of first-order recurrent neural networks by means of fuzzy rules
    Mantas, C. J.
    JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2019, 37 (03) : 4055 - 4070
  • [3] Extraction of fuzzy logic rules from data by means of artificial neural networks
    Holeña, M
    KYBERNETIKA, 2005, 41 (03) : 297 - 314
  • [4] Extraction of similarity based fuzzy rules from artificial neural networks
    Mantas, C. J.
    Puche, J. M.
    Mantas, J. M.
    INTERNATIONAL JOURNAL OF APPROXIMATE REASONING, 2006, 43 (02) : 202 - 221
  • [5] Creation of Digital Twins by Combining Fuzzy Rules with Artificial Neural Networks
    Lermer, Matthias
    Reich, Christoph
    45TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY (IECON 2019), 2019, : 5849 - 5854
  • [6] Extraction of similarity based fuzzy rules from artificial neural networks
    Mantas, C.J.
    Puche, J.M.
    Mantas, J.M.
    International Journal of Approximate Reasoning, 2006, 43 (02): : 202 - 221
  • [7] Fuzzy preprocessing rules for the improvement of an artificial neural network well log interpretation model
    Wong, KW
    Fung, CC
    Law, KW
    IEEE 2000 TENCON PROCEEDINGS, VOLS I-III: INTELLIGENT SYSTEMS AND TECHNOLOGIES FOR THE NEW MILLENNIUM, 2000, : 400 - 405
  • [8] Training artificial neural networks with fuzzy logic rules in data classification problems
    Kantardzic, MM
    Elmaghraby, AS
    INTELLIGENT SYSTEMS, 1997, : 170 - 173
  • [9] INTERPRETATION OF FUZZY DATA BY MEANS OF FUZZY RULES WITH APPLICATIONS TO SPEECH RECOGNITION
    CASACUBERTA, F
    VIDAL, E
    BENEDI, JM
    FUZZY SETS AND SYSTEMS, 1987, 23 (03) : 371 - 380
  • [10] Fuzzy rules extraction, reasoning and rules adaptation in fuzzy neural networks
    Kasabov, NK
    1997 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, 1997, : 2380 - 2383
12345