Knowledge extraction from neural networks using the all-permutations fuzzy rule base: The LED display recognition problem

被引：15

作者：

Kolman, Eyal ^{[1
]}

Margaliot, Michael ^{[1
]}

机构：

[1] Tel Aviv Univ, Sch Elect Engn Syst, IL-69978 Tel Aviv, Israel

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 2007年 / 18卷 / 03期

关键词：

feedforward neural networks; hybrid intelligent systems; knowledge extraction; neurofuzzy systems; rule extraction; rule generation;

D O I：

10.1109/TNN.2007.891686

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A major drawback of artificial neural networks (ANNs) is their black-box character. Even when the trained network performs adequately, it is very difficult to understand its operation. In this letter, we use the mathematical equivalence between ANNs and a specific fuzzy rule base to extract the knowledge embedded in the network. We demonstrate this using a benchmark problem: the recognition of digits produced by a light emitting diode (LED) device. The method provides a symbolic and comprehensible description of the knowledge learned by the network during its training.

引用

页码：925 / 931

页数：7

共 49 条

[21] Software Effort Prediction using Regression Rule Extraction from Neural Networks
Setiono, Rudy
Dejaeger, Karel
Verbeke, Wouter
Martens, David
Baesens, Bart
22ND INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI 2010), PROCEEDINGS, VOL 2, 2010, : 45 - 52
[22] Eclectic Rule Extraction from Neural Networks Using Aggregated Decision Trees
Al Iqbal, Md. Ridwan
2012 7TH INTERNATIONAL CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING (ICECE), 2012,
[23] Using a clustering genetic algorithm for rule extraction from artificial neural networks
Hruschka, ER
Ebecken, NFF
2000 IEEE SYMPOSIUM ON COMBINATIONS OF EVOLUTIONARY COMPUTATION AND NEURAL NETWORKS, 2000, : 199 - 206
[24] A penalty-function approach to rule extraction from knowledge-based neural networks
de Menezes, RM
Zaverucha, G
Barbosa, VC
ICONIP'98: THE FIFTH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING JOINTLY WITH JNNS'98: THE 1998 ANNUAL CONFERENCE OF THE JAPANESE NEURAL NETWORK SOCIETY - PROCEEDINGS, VOLS 1-3, 1998, : 1497 - 1500
[25] Fuzzy rule extraction from a feed forward neural network by training a representative fuzzy neural network using gradient descent
Brouwer, RK
2004 IEEE International Conference on Industrial Technology (ICIT), Vols. 1- 3, 2004, : 1168 - 1172
[26] Fuzzy rule extraction from a feed forward neural network by training a representative fuzzy neural network using gradient descent
Brouwer, RK
INTERNATIONAL JOURNAL OF UNCERTAINTY FUZZINESS AND KNOWLEDGE-BASED SYSTEMS, 2005, 13 (06) : 673 - 698
[27] Contour Tracking Based Knowledge Extraction And Object Recognition Using Deep Learning Neural Networks
Reddy, Annapareddy V. N.
Phanikrishna, Ch.
PROCEEDINGS ON 2016 2ND INTERNATIONAL CONFERENCE ON NEXT GENERATION COMPUTING TECHNOLOGIES (NGCT), 2016, : 352 - 354
[28] Rule extraction from neural networks trained using evolutionary algorithms with deterministic mutation
Fukumi, M
Akamatsu, N
IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE, 1998, : 686 - 689
[29] Rule extraction from trained adaptive neural networks using artificial immune systems
Kahramanli, Humar
Allahverdi, Novruz
EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (02) : 1513 - 1522
[30] Knowledge extraction in auction verification employing techniques from machine learning and fuzzy neural networks.
Souza, Paulo Vitor de Campos
Dragoni, Mauro
IEEE CONFERENCE ON EVOLVING AND ADAPTIVE INTELLIGENT SYSTEMS 2024, IEEE EAIS 2024, 2024, : 216 - 223

← 1 2 3 4 5 →