Limitations of the unique-attribute representation for a learning system
Conference Paper
Overview
Identity
Additional Document Info
Other
View All
Overview
abstract
Two problems faced by many learning systems are that learning can result in an overall increase in system performance time and that overgeneral knowledge can be learned, leading to incorrect system performance. We address these problems in an empirical study in the context of the Soar architecture. In this context, we discuss the development of a general unique-attribute representation of annotated models which is used to build a large application with learning capabilities. Besides verifying, on a large application, the previously-reported results regarding the efficiency benefits of a unique-attribute representation, we show how the unique-attribute representation can prevent learning overgeneral knowledge. However, our study also reveals the limitations of such a representation, illustrating the trade-offs involved in developing a representation for a large application. The limitations revealed are that overspecific knowledge can be learned due to the representation; programming within such a representation is more difficult than that within a multi-attribute representation; and proposing operators in parallel, which is essential for flexible problem solving, is problematic.
name of conference
Proceedings of 9th IEEE Conference on Artificial Intelligence for Applications
