Learning in Meta-Reasoning Architectures

Learning in Meta-Reasoning Architectures

MAX can learn when the rules and primitive operators needed for learning are included in the architecture and then invoked. The architecture explicitly facilitates learning by providing a homogeneous representation of knowledge and a declarative storage of knowledge. Logic frames can nest knowledge such that changes, including additions and deletions of logic, can be performed in a syntactically homogeneous manner. Learning in MAX involves self-modification to the architecture.


Return to the Issues Index for this Architecture.

Return to the top of this architecture.

Go to a Discussion of this issue for multiple architectures.


Current Location: Meta-Reasoning-Issues-Learning

Go to NEXT page.