A statistics based approach for extracting priority rules from trained neural networks

被引：9
|
作者：
Zhou, ZH [1 ]
Chen, SF [1 ]
Chen, ZQ [1 ]
机构：
[1] Nanjing Univ, State Key Lab Novel Software Technol, Nanjing, Peoples R China
来源：
IJCNN 2000: PROCEEDINGS OF THE IEEE-INNS-ENNS INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOL III | 2000年
关键词：
D O I：
10.1109/IJCNN.2000.861337
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this paper, a statistics based approach named STARE that is designed to extract symbolic rules from trained neural networks is proposed. STARE deals with continuous attributes in a unique way so that not only different attributes could be discretized to different number of clusters but also unnecessary discretization could be avoided. STARE introduces statistics to the generation and evaluation of priority rules that have concise appearance. Since it is independent of the network architectures and training algorithms, STARE could be applied to diversified neural classifiers. Experimental results show that rules extracted via STARE are comprehensible, compact and accurate.
引用
收藏
页码：401 / 406
页数：6
相关论文
共 50 条
  • [1] Extracting rules from trained neural networks
    Tsukimoto, H
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2000, 11 (02): : 377 - 389
  • [2] EXTRACTING RULES FROM TRAINED RBF NEURAL NETWORKS
    Grabusts, Peter
    ENVIRONMENT, TECHNOLOGY, RESOURCES, PROCEEDINGS, 2005, : 33 - 39
  • [3] Extracting boolean and probabilistic rules from trained neural networks
    Liu, Pengyu
    Melkman, Avraham A.
    Akutsu, Tatsuya
    NEURAL NETWORKS, 2020, 126 (300-311) : 300 - 311
  • [4] Effectively extracting rules from trained neural networks based on the characteristcs of the classification hypersurfaces
    Zhang, DX
    Liu, Y
    Wang, ZQ
    PROCEEDINGS OF 2005 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-9, 2005, : 1541 - 1546
  • [5] Extracting M-of-N rules from trained neural networks
    Setiono, R
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2000, 11 (02): : 512 - 519
  • [6] Survey and critique of techniques for extracting rules from trained artificial neural networks
    Andrews, R
    Diederich, J
    Tickle, AB
    KNOWLEDGE-BASED SYSTEMS, 1995, 8 (06) : 373 - 389
  • [7] Extracting rules from neural networks: A data mining approach
    Ludermir, TB
    Braga, AP
    Nobre, CN
    Carvalho, APL
    DATA MINING, 1998, : 303 - 314
  • [8] The truth is in there: Current issues in extracting rules from trained feedforward artificial neural networks
    Tickle, AB
    Golea, M
    Hayward, R
    Diederich, J
    1997 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, 1997, : 2530 - 2534
  • [9] Extracting propositions from trained neural networks
    Tsukimoto, H
    IJCAI-97 - PROCEEDINGS OF THE FIFTEENTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOLS 1 AND 2, 1997, : 1098 - 1105
  • [10] Extracting symbolic rules from trained neural network ensembles
    Zhou, ZH
    Jiang, Y
    Chen, SF
    AI COMMUNICATIONS, 2003, 16 (01) : 3 - 15
12345