Extracting Provably Correct Rules from Artificial Neural Networks

Although connectionist learning procedures have been applied successfully to a variety of real-world scenarios, artificial neural networks have often b en criticized for exhibiting a low degree of comprehensibility. Mechanisms that automatically compile neural networks into symbolic rules offer a promising perspective to overcome this practical shortcoming of neural network repres entations. This paper describes an approach to neural network rule extraction based on Validity Interval Analysis (VI-Analysis). VI-Analysis is a generic tool for extracting symbolic knowledge from Backpropagation-style artificial neural networks. It does this by propagating whole intervals of activations through the network in both the forward and backward directions. In the context of rule extraction, these intervals are used to prove or disprove the correctness of conjectured rules . We describe techniques for generating and testing rule hypotheses, and demonstrate these using some simple classification tasks including the MONK’s benchmark problems. Rules extracted by VI-Analysis are provably correct. No assumpt ions are made about the topology of the network at hand, as well as the procedure employed for training the network.

[1]  Ryszard S. Michalski,et al.  Comparing learning paradigms via diagrammatic visualization: a case study in single concept learning using symbolic, neural net and genetic algorithm methods , 1991 .

[2]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

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

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

[5]  Jude W. Shavlik,et al.  Interpretation of Artificial Neural Networks: Mapping Knowledge-Based Neural Networks into Rules , 1991, NIPS.

[6]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[7]  Terrence J. Sejnowski,et al.  NETtalk: a parallel network that learns to read aloud , 1988 .

[8]  Clayton McMillan.  Rule induction in a neural network through integrated symbolic and subsymbolic processing , 1992 .

[9]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[10]  John H. Holland,et al.  Genetic Algorithms and Adaptation , 1984 .

[11]  Michael C. Mozer,et al.  Rule Induction through Integrated Symbolic and Subsymbolic Processing , 1991, NIPS.

[12]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[13]  Geoffrey G. Towell,et al.  Symbolic knowledge and neural networks: insertion, refinement and extraction , 1992 .

[14]  Sebastian Thrun,et al.  Inversion in Time , 1990, EURASIP Workshop.

[15]  Jude W. Shavlik,et al.  Learning Symbolic Rules Using Artificial Neural Networks , 1993, ICML.

[16]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[17]  Narendra Karmarkar,et al.  A new polynomial-time algorithm for linear programming , 1984, Comb..

[18]  Raymond J. Mooney,et al.  Combining Neural and Symbolic Learning to Revise Probabilistic Rule Bases , 1992, NIPS.

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

[20]  J. Jeffrey Mahoney and Raymond J. Mooney,et al.  Combining Symbolic and Neural Learning to Revise Probabilistic Theories , 1992 .

[21]  Alexander H. Waibel,et al.  Modular Construction of Time-Delay Neural Networks for Speech Recognition , 1989, Neural Computation.

[22]  Dean Pomerleau,et al.  ALVINN, an autonomous land vehicle in a neural network , 2015 .

[23]  Philip H. W. Leong,et al.  ANN Based Classification for Heart Defibrillators , 1991, NIPS 1991.

[24]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[25]  L.-M. Fu,et al.  Integration of neural heuristics into knowledge-based inference , 1989, International 1989 Joint Conference on Neural Networks.