Bayesian model evidence

The probability of sensory data under a generative model; negative log evidence is bounded by free energy.

Neighborhood — ranked by edge-count

concept

Model Evidence
related_to
Probability of data under the model, penalizing complexity and rewarding accuracy.
free energy
associated_with
Thermodynamic potential ΔF = ΔE − TΔS; domain walls form if ΔF < 0

cosine ≥ 0.65 · no typed edge

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

Bayesian Model Selectionconcept0.844
Choosing among candidate models based on model evidence.
Bayesian Model-Based Reinforcement Learningframework0.818
RL variant that maintains beliefs over environment model; compared to active inference using Thompson sampling.
Bayesian Model Expansionmethod0.818
Adding new states or parameters to the generative model if it increases model evidence, enabling concept learning.
Bayesian Model Averagingconcept0.814
Predictions formed by averaging over policy-specific beliefs, weighted by policy probabilities.
Bayesian Inferencemethod0.812
Bayesian model reduction (method)method0.794
A method for simplifying models by removing parameters that don't contribute; applied to eliminate the self-boundary prior.
Natural Selection as Bayesian Model Selectionconcept0.780
Analogy between evolution (model selection) and Bayesian model reduction; but evolution is not curious or insightful
Bayesian Model of Painframework0.779
Conceptualization of pain perception as inference over hidden nociceptive causes, from Eckert et al. 2022