SOAR: an architecture for general intelligence
Artificial Intelligence
Unified theories of cognition
Eliminating combinatorics from production match
Eliminating combinatorics from production match
Chunking in Soar: The Anatomy of a General Learning Mechanism
Machine Learning
Learning efficient rules by maintaining the explanation structure
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 1
Hi-index | 0.00 |
This paper describes how a computational system for designing can learn useful, reusable, generalized search strategy rules from its own experience of designing. It can then apply this experience to transform the design process from search based (knowledge lean) to knowledge based (knowledge rich). The domain of application is the design of spatial layouts for architectural design. The processes of designing and learning are tightly coupled.