Hello - I'm just here to drop a somewhat vague/incipient idea for an AI model and see if there are any existing frameworks that could be used with it.
The general idea is to view agent action and perception as part of the same discrete data stream, and model intelligence as compression of sub-segments of this stream into independent "mechanisms" (patterns of action-perception) which can be used for prediction/action and potentially recombined into more general frameworks as the agent learns.
More precisely, I'm looking for: 1. The method of pattern representation 2. An algorithm for inferring initially orthogonal/unrelated patterns from the same data stream 3. Some manner of meta-learning for recombining mechanisms
Clearly this is a tall order, but please humor me and provide some feedback.
(For a conceptually similar model look at Friston's "Active Inference".)
[link] [comments]