Levels of Pattern Description in Learning

Abstract

A learning system a complex, real-world domain will require a significant amount of knowledge to be used order to (1) deal with large numbers of features, most of which are irrelevant, and (2) find similarities between the concepts that are inferred from the observed data. Use of knowledge-free, syntactic approaches to generalization complex environments will result a combinatorial explosion the number of possible generalizations. Moreover, the important semantic features are not in the data; rather they must be hypothesized using prior knowledge. The learning system described this paper uses a multi-level knowledge-directed approach order to cope with these problems. This paradigm is explored the action-oriented game of baseball. The system attempts to interpret observed activity terms of general knowledge provided about competitive games. This approach to learning can be viewed as a type of recognition, where the level of initial knowledge is general and where the specific observations mold a particular structure from the general knowledge. The system is organized into multiple levels of pattern descriptions, processing, and knowledge, reflecting the logical structure of the problem. In moving through those levels of description, the system filters out irrelevant features, hypothesizes additional semantic features (goals and relationships) and forms a hierarchy of generalized classes that extract the similarities the descriptions. Examples of learning by a working computer program are presented.