Combining Explanation-Based and Neural Learning: An Algorithm and Empirical Results

Machine learning is an area where both symbolic and neural approaches have been heavily investigated. However, there has been little research into the synergies achievable by combining these two learning paradigms. A hybrid approach that combines the symbolically-oriented explanation-based learning paradigm with the neural back-propagation algorithm is described. Most realistic problems can never be formalized exactly. However, there is much to be gained by utilizing the capability to reason nearly correctly. In the presented EBL-ANN algorithm, a “roughly-correct” explanatory capability leads to the acquisition of a classification rule that is almost correct. The rule is mapped into a neural network, where subsequent refinement improves it. This approach overcomes problems that arise when using imperfect domain theories to build explanations and addresses the problem of choosing a good initial neural network configuration. Empirical results show that the hybrid system more accurately learns concepts than an explanation-based system by itself and that the hybrid also learns them much faster than a neural learning system by itself. Combining Explanation-Based and Neural Learning: An Algorithm and Empirical Results