Bottom-up learning

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

• Bottom-up Selectionconcept0.818
• Learningconcept0.812
  Inference of parameters encoding contingencies of the world (e.g., likelihood matrix A) at slower timescale than perception.
• Bottom Up Controlconcept0.802
• Associative Learningconcept0.790
  Sentience criterion; capacity occurs even in gene regulatory networks and non-neural morphogenetic agents.
• bottom-up sensory informationconcept0.780
  Sensory input providing evidence that is integrated with priors.
• Perceptual Learningconcept0.777
  Process of inferring causes of sensory information; unified with value learning as integral aspects of free energy minimization.
• Deep Learningconcept0.773
  Learning hierarchical representations of non-decomposable functions; proposed as formal equivalent to ETI process.
• Bottom-up interpretabilityconcept0.772
  An interpretability paradigm that explains computation in the model's own terms, rather than imposing top-down abstractions; VPD aims to realize this.