Knowledge extraction from artificial neural network models

The paper describes the development and application of several techniques for knowledge extraction from trained ANN models, such as the identification of redundant inputs and hidden neurons, derivation of causal relationships between inputs and outputs, and analysis of the hidden neuron behavior in classification ANNs. An example of the application of these techniques is given of the faulty LED display benchmark. References of the application of these techniques are given of diverse large scale ANN models of industrial processes.

[1]  Keinosuke Fukunaga,et al.  Application of the Karhunen-Loève Expansion to Feature Selection and Ordering , 1970, IEEE Trans. Computers.

[2]  Walter Vandaele,et al.  Applied Time Series and Box-Jenkins Models , 1983 .

[3]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[4]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[5]  Thomas J. Mc Avoy,et al.  Use of Neural Nets For Dynamic Modeling and Control of Chemical Process Systems , 1989, 1989 American Control Conference.

[6]  Kenji Baba,et al.  Explicit representation of knowledge acquired from plant historical data using neural network , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[7]  Mark A. Kramer,et al.  Improvement of the backpropagation algorithm for training neural networks , 1990 .

[8]  Josiah C. Hoskins,et al.  Artificial neural network models for knowledge representation in chemical engineering , 1990 .

[9]  Jirí Benes,et al.  On neural networks , 1990, Kybernetika.

[10]  Mark A. Kramer,et al.  Autoassociative neural networks , 1992 .

[11]  Zvi Boger,et al.  Application of neural networks to water and wastewater treatment plant operation , 1992 .

[12]  Hugo Guterman,et al.  Application of principal component analysis to the design of neural networks , 1994, Neural Parallel Sci. Comput..

[13]  Zvi Boger,et al.  Application of neural networks for interpretation of ion mobility and x-ray fluorescence spectra , 1994 .

[14]  Zvi Boger,et al.  Use of Neural Networks for Quantitative Measurements in Ion Mobility Spectrometry (IMS) , 1994, J. Chem. Inf. Comput. Sci..

[15]  Ryotaro Kamimura,et al.  HIDDEN INFORMATION MAXIMIZATION FOR FEATURE DETECTION AND RULE DISCOVERY , 1995 .

[16]  Zvi Boger.  Experience in developing models of industrial plants by large scale artificial neural networks , 1995, Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems.

[17]  L. Ratton,et al.  Robust Classification of "Artificial Nose" Sensor Data by Artificial Neural Networks , 1997 .