Experimental Evaluation of Integrating Machine Learning

Machine learning and knowledge acquisition from experts have distinct knowledge acquisition capabilities that appear to be complementary. This study demonstrates that the integration of these approaches can both improve the accuracy of the knowledge base that is developed and reduce the time taken to develop it. In addition, users expected the expert systems created through the integrated approach to have higher accuracy than the expert systems created without machine learning and rated the integrated approach less diicult to use. They also provided favorable evaluations of both the speciic integrated software and of the general value of machine learning for knowledge acquisition. The system studied, called The Knowledge Factory, is distinguished by the manner in which it supports direct interaction with domain experts with little or no knowledge engineering expertise. The beneets reported relate to use by such users.