Bayesian model reduction formalises post-hoc hypothesis testing to simplify the generative model.

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

• Bayesian model reduction (method)method0.843
  A method for simplifying models by removing parameters that don't contribute; applied to eliminate the self-boundary prior.
• Bayesian model reduction after 12 trials correctly removes off-diagonal (redundant) parameters from the likelihood array, recovering the true contingency structure.finding0.833
  Validation that BMR correctly identifies and prunes wrong connections in the likelihood mapping
• In simulations, positive evidence threshold for Bayesian model reduction corresponds to ΔF ≤ −3, equivalent to odds ratio of exp(−3) ≈ 0.05 (reduced model ~20 times more likely than full model).finding0.824
  Quantitative threshold used for accepting reduced models; linked to Bayes factor of ~20
• Friston & Penny (2011) — Post hoc Bayesian model selectionconcept0.820
  Source paper for Bayesian model reduction methodology used in structure learning
• Structure learning via Bayesian model reduction has a clear biological interpretation in terms of synaptic decay and switching off certain synaptic connections, reminiscent of REM sleep.claim0.795
  Biological interpretation of Bayesian model reduction.
• prior eliminated by Bayesian model reductionconcept0.794
  Bayesian model reduction removes the structural partition prior once evidence shows it is unnecessary, yielding a post-dual agent.
• Bayesian Model Reduction (BMR)framework0.792
  Formal mechanism by which the separation prior sigma is pruned from the generative model
• Bayesian model expansion allows for generalisation and concept learning in active inference.claim0.790
  Definition of Bayesian model expansion, Section 9.2.