A fast method for rule extraction in neural networks

被引：0

作者：

Grau, MMA ^{[1
]}

Molinero, LDH ^{[1
]}

机构：

[1] Univ Granada, Dept Lenguajes & Sistemas Informat, E-18071 Granada, Spain

来源：

IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE | 1998年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Most methods for finding regularities or rule extraction based data start out from the idea that the representation of the data must evolve from a distributed representation of the information to a more localised representation which will represent the skeleton of the network. This idea involves the problem of needing long training times imposed by the back propagation algorithm, as well as the errors deriving from incorrect elimination of connections and units in order to extract the structure of the network. The method proposed here, which I call Direct Method for Structural Learning, allows the appropriate learning and pruning to be achieved in a very short time due to the fact that it starts with a non-skeletal local representation of the network.

引用

页码：2334 / 2339

页数：6

共 50 条

[21] Rule Extraction from Trained Artifical Neural Networks
Peter Géczy
Shiro Usui
Behaviormetrika, 1999, 26 (1) : 89 - 106
[22] Fuzzy arithmetic in neural networks for linguistic rule extraction
Nii, Manabu
Ishibuchi, Hisao
International Conference on Knowledge-Based Intelligent Electronic Systems, Proceedings, KES, 1998, 2 : 387 - 394
[23] DeepRED - Rule Extraction from Deep Neural Networks
Zilke, Jan Ruben
Mencia, Eneldo Loza
Janssen, Frederik
DISCOVERY SCIENCE, (DS 2016), 2016, 9956 : 457 - 473
[24] Generalized analytic rule extraction for feedforward neural networks
Gupta, A
Park, S
Lam, SM
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 1999, 11 (06) : 985 - 991
[25] Neural Networks and Structured Knowledge: Rule Extraction and Applications
Franz J. Kurfess
Applied Intelligence, 2000, 12 : 7 - 13
[26] Designing a decompositional rule extraction algorithm for neural networks
Chen, Jen-Cheng
Heh, Jia-Sheng
Chang, Maiga
ADVANCES IN NEURAL NETWORKS - ISNN 2006, PT 1, 2006, 3971 : 1305 - 1311
[27] Fuzzy arithmetic in neural networks for linguistic rule extraction
Nii, M
Ishibuchi, H
1998 SECOND INTERNATIONAL CONFERENCE ON KNOWLEDGE-BASED INTELLIGENT ELECTRONIC SYSTEMS, KES '98, PROCEEDINGS, VOL 2, 1998, : 387 - 394
[28] Rule extraction from neural networks for intrusion detection in computer networks
Hofmann, A
Schmitz, C
2003 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS, VOLS 1-5, CONFERENCE PROCEEDINGS, 2003, : 1259 - 1265
[29] Experimental study of evolutionary based method of rule extraction from neural networks in medical data
Markowska-Kaczmar, Urszula
Matkowski, Rafal
ADVANCES IN DATA MINING: APPLICATIONS IN MEDICINE, WEB MINING, MARKETING, IMAGE AND SIGNAL MINING, 2006, 4065 : 76 - 90
[30] A new method for constructing granular neural networks based on rule extraction and extreme learning machine
Xu, Xinzheng
Wang, Guanying
Ding, Shifei
Jiang, Xiangying
Zhao, Zuopeng
PATTERN RECOGNITION LETTERS, 2015, 67 : 138 - 144

← 1 2 3 4 5 →