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

页码：401 / 406

页数：6

共 50 条

[21] Extracting rules from artificial Neural Networks with kernel-based representations
Ramírez, JM
ENGINEERING APPLICATIONS OF BIO-INSPIRED ARTIFICIAL NEURAL NETWORKS, VOL II, 1999, 1607 : 68 - 77
[22] Rules extraction from constructively trained neural networks based on genetic algorithms
Mohamed, Marghny H.
NEUROCOMPUTING, 2011, 74 (17) : 3180 - 3192
[23] Extracting Classification Rules from Artificial Neural Network Trained with Discretized Inputs
Dounia Yedjour
Neural Processing Letters, 2020, 52 : 2469 - 2491
[24] Extracting Classification Rules from Artificial Neural Network Trained with Discretized Inputs
Yedjour, Dounia
NEURAL PROCESSING LETTERS, 2020, 52 (03) : 2469 - 2491
[25] Evolving rules from neural networks trained on continuous data
Keedwell, E
Narayanan, A
Savic, D
PROCEEDINGS OF THE 2000 CONGRESS ON EVOLUTIONARY COMPUTATION, VOLS 1 AND 2, 2000, : 639 - 645
[26] Generating fuzzy if-then rules from trained neural networks: Linguistic analysis of neural networks
Ishibuchi, H
Nii, M
ICNN - 1996 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS. 1-4, 1996, : 1133 - 1138
[27] Evolving fuzzy neural networks for extracting rules
Yao, SS
Wei, CJ
He, ZY
FUZZ-IEEE '96 - PROCEEDINGS OF THE FIFTH IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, VOLS 1-3, 1996, : 361 - 367
[28] Evolving　Fuzzy　Neural　Networks　for　Extracting　Rules
He Zhenya Yao Susu Wei Chengjian (Department of Radio Engineering
Southeast University
Nanjing 210096)
通信学报 , 1997, (03) : 84 - 91
[29] Extracting rules from pruned neural networks for breast cancer diagnosis
Setiono, R
ARTIFICIAL INTELLIGENCE IN MEDICINE, 1996, 8 (01) : 37 - 51
[30] A DEXiRE for Extracting Propositional Rules from Neural Networks via Binarization
Contreras, Victor
Marini, Niccolo
Fanda, Lora
Manzo, Gaetano
Mualla, Yazan
Calbimonte, Jean-Paul
Schumacher, Michael
Calvaresi, Davide
ELECTRONICS, 2022, 11 (24)

← 1 2 3 4 5 →