Symbolic interpretation of artificial neural networks using genetic algorithms

被引:2
|
作者
Yedjour, Dounia [1 ]
Benyettou, Abdelkader [1 ]
Yedjour, Hayat [1 ]
机构
[1] Univ Sci & Technol dOran Mohamed Boudiaf, Dept Comp Sci, Signal Image Parole Lab, El Mnaouer, Oran, Algeria
关键词
Neural networks; rule extraction; genetic algorithm; RULE EXTRACTION;
D O I
10.3906/elk-1801-75
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The knowledge acquired during the learning of artificial neural networks (ANNs) is coded as values in synaptic weights, which makes their interpretations difficult, hence the name of the black box. The aim of this work is to provide a comprehensible interpretation of the ANN's decisions by extracting symbolic rules. We improve the performance of our extraction algorithm by combining the ANN with a genetic algorithm. Misleading rules whose support and confidence values are less than fixed thresholds are removed and, as a result, the comprehensibility is improved. The extracted rules are evaluated and compared with other works. The results show good performance of our proposal in terms of fidelity and accuracy.
引用
收藏
页码:2465 / 2475
页数:11
相关论文
共 50 条
  • [1] Symbolic interpretation of artificial neural networks based on multiobjective genetic algorithms and association rules mining
    Yedjour, Dounia
    Benyettou, Abdelkader
    [J]. APPLIED SOFT COMPUTING, 2018, 72 : 177 - 188
  • [2] Symbolic interpretation of artificial neural networks
    Taha, IA
    Ghosh, J
    [J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 1999, 11 (03) : 448 - 463
  • [3] Applying genetic and symbolic learning algorithms to extract rules from Artificial Neural Networks
    Milaré, CR
    Batista, GEAPA
    de Carvalho, ACPLF
    Monard, MC
    [J]. MICAI 2004: ADVANCES IN ARTIFICIAL INTELLIGENCE, 2004, 2972 : 833 - 843
  • [4] On the parallelization of artificial neural networks and genetic algorithms
    Adamidis, P
    Petridis, V
    [J]. INTERNATIONAL JOURNAL OF COMPUTER MATHEMATICS, 1998, 67 (1-2) : 105 - 125
  • [5] Artificial neural networks and genetic algorithms in QSAR
    Niculescu, SP
    [J]. JOURNAL OF MOLECULAR STRUCTURE-THEOCHEM, 2003, 622 (1-2): : 71 - 83
  • [6] Shape reconstruction by genetic algorithms and artificial neural networks
    Liu, XY
    Tang, MX
    Frazer, JH
    [J]. 6TH WORLD MULTICONFERENCE ON SYSTEMICS, CYBERNETICS AND INFORMATICS, VOL VI, PROCEEDINGS: INDUSTRIAL SYSTEMS AND ENGINEERING I, 2002, : 91 - 96
  • [7] Application of An Improved Genetic Algorithms in Artificial Neural Networks
    Shi, Huawang
    Yong Deng
    [J]. ISIP: 2009 INTERNATIONAL SYMPOSIUM ON INFORMATION PROCESSING, PROCEEDINGS, 2009, : 263 - +
  • [8] Shape reconstruction by genetic algorithms and artificial neural networks
    Liu, XY
    Tang, MX
    Frazer, JH
    [J]. ENGINEERING COMPUTATIONS, 2003, 20 (1-2) : 129 - 151
  • [9] Using neural networks and genetic algorithms as building blocks for artificial life simulations
    Beuster, G
    [J]. ARTIFICIAL NEURAL NETS AND GENETIC ALGORITHMS, 2001, : 363 - 366
  • [10] Knowledge Discovery in Medical Mining by using Genetic Algorithms and Artificial Neural Networks
    Srivathsa, P. K.
    [J]. 2ND INTERNATIONAL CONFERENCE ON METHODS AND MODELS IN SCIENCE AND TECHNOLOGY (ICM2ST-11), 2011, 1414