Rule extraction from neural networks via decision tree induction

被引：0

作者：

Sato, M ^{[1
]}

Tsukimoto, H ^{[1
]}

机构：

[1] Toshiba Co Ltd, Ctr Res & Dev, Saiwai Ku, Kawasaki, Kanagawa 2128582, Japan

来源：

IJCNN'01: INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS | 2001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：

Rule extraction from neural networks is the task for obtaining comprehensible descriptions that approximate the predictive behavior of neural networks. Rule-extraction algorithms are used for both interpreting neural networks and mining the relationship between input and output variables in data. This paper describes a new rule extraction algorithm that extracts rules that contain both continuous (real-valued) and discrete literals. This algorithm decomposes a neural network using decision trees and obtains production rules by merging the rules extracted from each tree. Results tested on the databases in UCI repository are presented.

引用

页码：1870 / 1875

页数：6

共 50 条

[41] Learning Accurate and Interpretable Decision Rule Sets from Neural Networks
Qiao, Litao
Wang, Weijia
Lin, Bill
THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 4303 - 4311
[42] RULE EXTRACTION FROM MINIMAL NEURAL NETWORKS FOR CREDIT CARD SCREENING
Setiono, Rudy
Baesens, Bart
Mues, Christophe
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 2011, 21 (04) : 265 - 276
[43] A METHOD OF RULE EXTRACTION FROM REGRESSION NEURAL NETWORKS FOR CREDIT RATING
Popov, Elena
AMIS 2010 - PROCEEDINGS OF THE 5TH INTERNATIONAL CONFERENCE, ACCOUNTING AND MANAGEMENT INFORMATION SYSTEMS, 2010, : 345 - 356
[44] DENAS Automated Rule Generation by Knowledge Extraction from Neural Networks
Chen, Simin
Bateni, Soroush
Grandhi, Sampath
Li, Xiaodi
Liu, Cong
Yang, Wei
PROCEEDINGS OF THE 28TH ACM JOINT MEETING ON EUROPEAN SOFTWARE ENGINEERING CONFERENCE AND SYMPOSIUM ON THE FOUNDATIONS OF SOFTWARE ENGINEERING (ESEC/FSE '20), 2020, : 813 - 825
[45] Rule extraction from artificial neural networks for voltage security analysis
Abrao, PJ
da Silva, APA
de Souza, ACZ
PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3, 2002, : 2126 - 2131
[46] Rule extraction from convolutional neural networks for heart disease prediction
Chakraborty, Manomita
BIOMEDICAL ENGINEERING LETTERS, 2024, 14 (04) : 649 - 661
[47] Cleavage site analysis using rule extraction from neural networks
Cho, YJ
Kim, H
ADVANCES IN NATURAL COMPUTATION, PT 1, PROCEEDINGS, 2005, 3610 : 1002 - 1008
[48] A METHOD OF RULE EXTRACTION FROM TRAINED NEURAL NETWORKS FOR CREDIT RATING
Popov, Elena
ECONOMIC WORLD DESTINY: CRISIS AND GLOBALIZATION?, SECTION IV: BANKING, ACCOUNTING AND FINANCIAL SYSTEMS FROM THE 21ST CENTURY PERSPECTIVE, 2010, : 637 - 642
[49] Exact and Approximate Rule Extraction from Neural Networks with Boolean Features
Mereani, Fawaz A.
Howe, Jacob M.
IJCCI: PROCEEDINGS OF THE 11TH INTERNATIONAL JOINT CONFERENCE ON COMPUTATIONAL INTELLIGENCE, 2019, : 424 - 433
[50] Rule extraction from trained neural networks using genetic algorithms
Arbatli, AD
Akin, HL
NONLINEAR ANALYSIS-THEORY METHODS & APPLICATIONS, 1997, 30 (03) : 1639 - 1648

← 1 2 3 4 5 →