Explanation Based Learning: A Comparison of Symbolic and Neural Network Approaches

Explanation based learning has typically been considered a symbolic learning method. An explanation based learning method that utilizes purely neural network representations (called EBNN) has recently been developed, and has been shown to have several desirable properties, including robustness to errors in the domain theory. This paper briefly summarizes the EBNN algorithm, then explores the correspondence between this neural network based EBL method and EBL methods based on symbolic representations. 1 Introduction Explanation based learning (EBL) is an important paradigm for machine learning because it offers a means of using prior knowledge to generalize more correctly from fewer training examples. EBL was originally conceived as a symbolic learning method ([DeJong and Mooney1986], [Mitchell et al.1986]), based on creating and analyzing explanations derived from symbolic rules. While it has been used successfully to learn control knowledge to speed up search ([Laird et al.1988], [Mi..