Combining Prior Symbolic Knowledge and Constructive Neural Network Learning

Abstract The concepts of knowledge-based systems and machine learning are combined by integrating an expert system and a constructive neural networks learning algorithm. Two approaches are explored: embedding the expert system directly and converting the expert system rule base into a neural network. This initial system is then extended by constructively learning additional hidden units in a problem-specific manner. Experiments performed indicate that generalization of a combined system surpasses that of each system individually.

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

[2]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[3]  Jadzia Cendrowska,et al.  PRISM: An Algorithm for Inducing Modular Rules , 1987, Int. J. Man Mach. Stud..

[4]  George F. Luger,et al.  Artificial Intelligence and the Design of Expert Systems , 1990 .

[5]  Frederick Hayes-Roth,et al.  Building expert systems , 1983, Advanced book program.

[6]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[7]  W S McCulloch,et al.  A logical calculus of the ideas immanent in nervous activity , 1990, The Philosophy of Artificial Intelligence.

[8]  James A. Anderson,et al.  Neurocomputing: Foundations of Research , 1988 .

[9]  Sholom M. Weiss,et al.  Computer Systems That Learn , 1990 .

[10]  J. Nadal,et al.  Learning in feedforward layered networks: the tiling algorithm , 1989 .

[11]  Eric B. Baum,et al.  Neural net algorithms that learn in polynomial time from examples and queries , 1991, IEEE Trans. Neural Networks.

[12]  Jude Shavlik,et al.  Refinement ofApproximate Domain Theories by Knowledge-Based Neural Networks , 1990, AAAI.

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

[14]  Zoran Obradovic,et al.  Parallel and distributed systems for constructive neural network learning , 1993, [1993] Proceedings The 2nd International Symposium on High Performance Distributed Computing.

[15]  Stephen I. Gallant,et al.  Perceptron-based learning algorithms , 1990, IEEE Trans. Neural Networks.

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

[17]  Jon Louis Bentley,et al.  Multidimensional binary search trees used for associative searching , 1975, CACM.