Survey and critique of techniques for extracting rules from trained artificial neural networks

It is becoming increasingly apparent that, without some form of explanation capability, the full potential of trained artificial neural networks (ANNs) may not be realised. This survey gives an overview of techniques developed to redress this situation. Specifically, the survey focuses on mechanisms, procedures, and algorithms designed to insert knowledge into ANNs (knowledge initialisation), extract rules from trained ANNs (rule extraction), and utilise ANNs to refine existing rule bases (rule refinement). The survey also introduces a new taxonomy for classifying the various techniques, discusses their modus operandi, and delineates criteria for evaluating their efficacy.

[1]  Jude Shavlik,et al.  THE EXTRACTION OF REFINED RULES FROM KNOWLEDGE BASED NEURAL NETWORKS , 1993 .

[2]  Johanna D. Moore,et al.  A Reactive Approach to Explanation , 1989, IJCAI.

[3]  Edward H. Shortliffe,et al.  Production Rules as a Representation for a Knowledge-Based Consultation Program , 1977, Artif. Intell..

[4]  C. L. Giles,et al.  Heuristics for the extraction of rules from discrete-time recurrent neural networks , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[5]  G. Nigel Gilbert,et al.  Explanation and dialogue , 1989, The Knowledge Engineering Review.

[6]  Sebastian Thrun,et al.  Extracting Provably Correct Rules from Artificial Neural Networks , 1993 .

[7]  Sebastian Thrun,et al.  The MONK''s Problems-A Performance Comparison of Different Learning Algorithms, CMU-CS-91-197, Sch , 1991 .

[8]  C. L. Giles,et al.  Rule refinement with recurrent neural networks , 1993, IEEE International Conference on Neural Networks.

[9]  C. Lee Giles,et al.  Learning and Extracting Finite State Automata with Second-Order Recurrent Neural Networks , 1992, Neural Computation.

[10]  Yoshiki Uchikawa,et al.  On fuzzy modeling using fuzzy neural networks with the back-propagation algorithm , 1992, IEEE Trans. Neural Networks.

[11]  Jude W. Shavlik,et al.  Using Sampling and Queries to Extract Rules from Trained Neural Networks , 1994, ICML.

[12]  Saman K. Halgamuge,et al.  Neural networks in designing fuzzy systems for real world applications , 1994 .

[13]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[14]  Michael C. Mozer,et al.  The Connectionist Scientist Game: Rule Extraction and Refinement in a Neural Network , 1991 .

[15]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

[16]  Hiroyuki Okada,et al.  Knowledge-based neural network: using fuzzy logic to initialize a multilayerd neural network and interpret postlearning results , 1993 .

[17]  Sushmita Mitra,et al.  Fuzzy MLP based expert system for medical diagnosis , 1994, CVPR 1994.

[18]  Stephen I. Gallant,et al.  Connectionist expert systems , 1988, CACM.

[19]  LiMin Fu,et al.  Rule Learning by Searching on Adapted Nets , 1991, AAAI.

[20]  Hamid R. Berenji,et al.  Refinement of Approximate Reasoning-based Controllers by Reinforcement Learning , 1991, ML.

[21]  LiMin Fu,et al.  Rule Generation from Neural Networks , 1994, IEEE Trans. Syst. Man Cybern. Syst..

[22]  Gerald Estrin,et al.  A reactive approach to explanation in expert and advice-giving systems , 1989 .

[23]  C. Lee Giles,et al.  Extraction, Insertion and Refinement of Symbolic Rules in Dynamically Driven Recurrent Neural Networks , 1993 .

[24]  Raymond L. Watrous,et al.  Induction of Finite-State Languages Using Second-Order Recurrent Networks , 1992, Neural Computation.

[25]  Tharam S. Dillon,et al.  Automated knowledge acquisition , 1994, Prentice Hall International series in computer science and engineering.

[26]  Volker Tresp,et al.  Network Structuring and Training Using Rule-Based Knowledge , 1992, NIPS.

[27]  R. Nakano,et al.  Medical diagnostic expert system based on PDP model , 1988, IEEE 1988 International Conference on Neural Networks.