Probably Approximately Correct Pac Learning

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Physical learningframework0.731
  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
• Learningconcept0.728
  Inference of parameters encoding contingencies of the world (e.g., likelihood matrix A) at slower timescale than perception.
• Associative Learningconcept0.723
  Sentience criterion; capacity occurs even in gene regulatory networks and non-neural morphogenetic agents.
• Perceptual Learningconcept0.721
  Process of inferring causes of sensory information; unified with value learning as integral aspects of free energy minimization.
• what is the 'correct number of features' for dictionary learning, and is this question well-posed?question0.714
  Open question about whether there is a true discrete feature count or a continuous splitting process
• Preference Learningconcept0.712
  The ability of active inference agents to learn their own prior preferences over outcomes by accumulating Dirichlet parameters from experience.
• Approximate Posterior (Q)concept0.710
  Factorised distribution used to approximate the true Bayesian posterior.
• Q-learningmethod0.706
  Model-free RL algorithm used in experimental comparison; employs ε-greedy exploration.