framework
active
framework:probably-approximately-correct-pac-learningProbably Approximately Correct Pac Learning
Neighborhood — ranked by edge-count
Thinkers (1)
thinker
- Lesley Valiantassociated_with
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Framework for solving inverse problems in which physical systems autonomously adapt their parameters in response to stimuli through local learning rules, without requiring computational design or explicit cost functions
- Inference of parameters encoding contingencies of the world (e.g., likelihood matrix A) at slower timescale than perception.
- Sentience criterion; capacity occurs even in gene regulatory networks and non-neural morphogenetic agents.
- Process of inferring causes of sensory information; unified with value learning as integral aspects of free energy minimization.
- Shows the passive vs. active divide is more important than the specific wording of instructions.
- what is the 'correct number of features' for dictionary learning, and is this question well-posed?question0.714Open question about whether there is a true discrete feature count or a continuous splitting process
- From paraphrasing results.
- Evidence against encoded reasoning.