method
active
method:belief-propagation

Belief Propagation

Inference mechanism underlying active inference; updates posterior beliefs via gradient descent on free energy.

Neighborhood — ranked by edge-count

Frameworks (1)

framework
  • Foundational framework by Karl Friston; the paper extends it to three hierarchical levels for modeling meta-awareness.

Methods (2)

method
  • Message passing algorithm based on Bethe approximation.
  • Mathematical framework for approximating posterior beliefs; converts exact Bayesian inference into optimization.

Claims (1)

claim

Related by similarity (8)

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.

  • Belief Shiftconcept0.800
    Change in the model's internal belief state as tracked by probes during CoT generation, indicating genuine uncertainty resolution
  • Property that additive modifications to activations affect all downstream computations, enabling tractable behavioral control
  • Belief Updatingconcept0.791
    Recursive inference of hidden states and parameters using free energy minimization.
  • Back-propagationmethod0.770
    Standard learning algorithm for deep neural networks that propagates error signals to adjust weights; lacks convergence guarantee for non-linearly separable functions
  • Friston et al. concept for collective belief dynamics; relevant for extended cognitive glue.
  • Schwitzgebel's concept applying behavioural and cognitive dispositions to LMs without ascriptions of phenomenal consciousness.
  • Algorithmic framework for probabilistic inference in graphical models.
  • Pain-Beliefconcept0.745
    The latent state inferred by the agent representing its belief about being in pain, used as exploration signal