Bayesian Surprise

KL divergence between prior and posterior beliefs; used in visual salience.

Neighborhood — ranked by edge-count

paper

concept

Mutual Information
associated_with
Expected mutual information between future states and outcomes; equivalent to intrinsic value.

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 Inferencemethod0.844
Bayesian inversionconcept0.812
Online inversion of nonlinear dynamic causal models using DEM.
Surpriseconcept0.812
The negative log probability of sensory samples; minimized by free energy.
Bayesian Brain Hypothesisframework0.781
Normative theory proposing biological systems perform approximate Bayesian inference through free energy minimization.
Bayesian Cognitive Scienceframework0.773
Umbrella framework for brain-centric Bayesian approaches; contrasted with active inference
Surprise (Surprisal)concept0.769
Negative log probability of an outcome under the generative model; minimized in active inference.
Bayesian orderframework0.769
The partial order on classical probability distributions (Delta^n) that makes Shannon entropy a measurement on a domain.
Bayesian Mechanicsframework0.768