Multi-Method Learning

As a capability, learning is often thought of as one of the necessary conditions for intelligence in an agent. Some systems extend this requirement by including a plethora of mechanisms for learning in order to obtain obtain as much as possible from the system, or to allow various components of their system to learn in their own ways (depending on the modularity, representation, etc., of each). On the other hand, mutltiple methods are included in a system in order to guage the performance of one method against that of another.
The following architectures integrate multiple learning methods:


Press UP to go to the list of capabilties.

Press HOME to go to the Table of Contents.