Article

Current trends on knowledge extraction and neural networks

Authors:

David A. Elizondo,

Mario A. GóngoraAuthors Info & Claims

ICANN'05: Proceedings of the 15th international conference on Artificial neural networks: formal models and their applications - Volume Part II

Pages 485 - 490

Published: 11 September 2005 Publication History

Abstract

The extraction of knowledge from trained neural networks provides a way for explaining the functioning of a neural network. This is important for artificial networks to gain a wider degree of acceptance. An increasing amount of research has been carried out to develop mechanisms, procedures and techniques for extracting knowledge from trained neural networks. This publication presents some of the current research trends on extracting knowledge from trained neural networks.

References

[1]

Elizondo, D.A., McClendon, R.W., Hoogenboom, G.: Neural network models for predicting flowering and physiological maturity of soybean. Transactions of the ASAE 37 (1994) 981- 988

[2]

Shellhammer, I., Diederich, J., Towsey, J., Brugman, C.: Knowledge extraction and recurrent neural networks: An analysis of an elman network trained on a natural language learning task. In: Proceedings of the Joint Conference on New Methods in Language Processing and Computational Natural Language Learning, Association for Computational Linguistics (1998) 73-78

Digital Library

[3]

Chiang Tan, S., Peng Lim, C.: Application of an adaptive neural network with symbolic rule extraction to fault detection and diagnosis in a power generation plant. IEEE Transactions on Energy Conversion 19 (2004) 369-377

[4]

Tajine, M., Elizondo, D.: The recursive deterministic perceptron neural network. Neural Networks 11 (1998) 1571-1588

Digital Library

[5]

Tajine, M., Elizondo, D.: Growing methods for constructing recursive deterministic perceptron neural networks and knowledge extraction. Artificial Intelligence 102 (1998) 295-322

Digital Library

[6]

Browne, A., Hudson, B., Whitley, D., Ford, M., Picton, P., Kazemian, H.: Knowledge extraction from neural networks. In: Proceedings of the IEEE Industrial Electronics Society 29th Annual Conference (IECON-03), IEEE (2003) 1909-1913

[7]

Setiono, R., Pan, S.L., Hsieh, M.H., Azcarraga, A.P.: Separating core and noncore knowledge: An application of neural network rule extraction to a cross-national study of brand image perception. IEEE Transactions on Systems, Man and Cybernetics-Part C: Applications and Reviews PP (2005) 1-11

Digital Library

[8]

Fu, X., Wang, L.: Rule extraction using a novel gradient-based method and data dimensionality reduction. In: Proceedings of the International Joint Conference on Neural Networks (IJCNN). Volume 2. (2002) 1275-1280

[9]

Dorado, J., Rabunal, J.R., Rivero, D., Santos, A., Pazos, A.: Automatic recurrent ann rule extraction with genetic programming. In: Proceedings of the International Joint Conference on Neural Networks (IJCNN). Volume 2. (2002) 1552-1557

[10]

Qi, W., Bo, Y., Jie, Z.: Extracted rules from software quality prediction model based on neural networks. In: International Conference on Tools with Artificial Intelligence. (2004) 191-195

Digital Library

[11]

Gorban, A.N., Mirkes, E.M., Tsaregorodtsev, V.G.: Generation of explicit knowledge from empirical data through pruning of trainable neural networks. In: Proceedings of the International Joint Conference on Neural Networks (IJCNN) San Diego, IEEE Neural Networks Council; Edward Brothers (1999)

[12]

Yao, J.: Knowledge based descriptive neural networks. In: Proceedings of the 9th International Conference on Rough Sets, Fuzzy Sets, Data Mining and Granular Computing. Number 2639 (2003) 430-436

Digital Library

[13]

Hong, X., Harris, C.J.: A neurofuzzy network knowledge extraction and extended gramschmidt algorithm for model subspace decomposition. IEEE Transactions on Fuzzy Systems 11 (2003) 538-541

Digital Library

[14]

Iyatomi, H.: Knowledge extraction from scenery images and recognition using fuzzy inference neural networks. Electronics and Communication in Japan, Part 2 86 (2003) 82-90

[15]

Fan, T.G., Wang, X.Z.: A new approach to weighted fuzzy production rule extraction from neural networks. In: Proceedings of the International Conference on Machine Learning and Cybernetics. Volume 6. (2004) 3348-3351

[16]

Sudheer, K.P., Jain, A.: Explaining the internal behaviour of artificial neural network river flow models. Hydrological Processes 18 (2004) 833-844

[17]

Mitsdorffer, R., Diederich, J., Tan, C.: Rule extraction from technology ipos in the us stock market. In: Proceedings of the 9th International Conference on Neural Information Processing (ICONIP). Volume 5. (2002) 2338-2334

[18]

Yue, L., Hui, L., Bofend, Z., Gengfend, W.: Extraction of if-then rules from trained neural networks and its application to eartchquake prediction. In: Proceedings of the 3rd IEEE International COnference on Cognitive Informatics. (2004) 109-115

Digital Library

[19]

Remm, J.F., Aexandre, F.: Knowledge extraction using artificial neural networks: application to radar traget identification. Signal Processing 82 (2002) 117-120

Digital Library

Cited By

Elizondo DBirkenhead RGamez MGarcia NAlfaro E(2012)Linear separability and classification complexityExpert Systems with Applications: An International Journal10.1016/j.eswa.2012.01.09039:9(7796-7807)Online publication date: 1-Jul-2012
https://dl.acm.org/doi/10.1016/j.eswa.2012.01.090
Elizondo DBirkenhead RGóngora MTaillard ELuyima P(2007)Analysis and test of efficient methods for building recursive deterministic perceptron neural networksNeural Networks10.1016/j.neunet.2007.07.00920:10(1095-1108)Online publication date: 1-Dec-2007
https://dl.acm.org/doi/10.1016/j.neunet.2007.07.009

Recommendations

Knowledge extraction and recurrent neural networks: an analysis of an Elman network trained on a natural language learning task
NeMLaP3/CoNLL '98: Proceedings of the Joint Conferences on New Methods in Language Processing and Computational Natural Language Learning

We present results of experiments with Elman recurrent neural networks (Elman, 1990) trained on a natural language processing task. The task was to learn sequences of word categories in a text derived from a primary school reader. The grammar induced by ...
Classification Tree Extraction from Trained Artificial Neural Networks

Recent advances in neural networks design and training provoked the 2nd artificial neural networks (ANN) renaissance. In many cases classification decision made by trained fully connected neural nets is better than that acquired by models like C4.5 or ...
Knowledge Extraction from Transducer Neural Networks

Previously neural networks have shown interesting performance results for tasks such as classification, but they still suffer from an insufficient focus on the structure of the knowledge represented therein. In this paper, we analyze various knowledge ...

Comments

Information & Contributors

Information

Published In

cover image Guide Proceedings

ICANN'05: Proceedings of the 15th international conference on Artificial neural networks: formal models and their applications - Volume Part II

September 2005

1035 pages

ISBN:3540287558

Editors:
Włodzisław Duch
Nicolaus Copernicus University, Department of Informatics, Toruń, Poland and Nanyang Technological University, School of Computer Engineering, Singapore
,
Janusz Kacprzyk
Polish Academy of Sciences, Systems Research Institute, Warsaw, Poland
,
Sławomir Zadrożny
Polish Academy of Sciences, Systems Research Institute, Warsaw, Poland
,
Erkki Oja
Helsinki University of Technology, Hut, Finland

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 11 September 2005

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 13 Aug 2024

Other Metrics

View Author Metrics

Citations

Cited By

Elizondo DBirkenhead RGamez MGarcia NAlfaro E(2012)Linear separability and classification complexityExpert Systems with Applications: An International Journal10.1016/j.eswa.2012.01.09039:9(7796-7807)Online publication date: 1-Jul-2012
https://dl.acm.org/doi/10.1016/j.eswa.2012.01.090
Elizondo DBirkenhead RGóngora MTaillard ELuyima P(2007)Analysis and test of efficient methods for building recursive deterministic perceptron neural networksNeural Networks10.1016/j.neunet.2007.07.00920:10(1095-1108)Online publication date: 1-Dec-2007
https://dl.acm.org/doi/10.1016/j.neunet.2007.07.009

View Options

View options

Media

Figures

Other

Tables

View Table of Contents