method
active
method:mean-field-approximationMean-Field Approximation
Variational technique used in active inference to tractably compute posterior beliefs.
Neighborhood — ranked by edge-count
Papers (1)
paper
Frameworks (1)
framework
- Active InferenceusesFoundational framework by Karl Friston; the paper extends it to three hierarchical levels for modeling meta-awareness.
Concepts (1)
concept
- free energyimplementsThermodynamic potential ΔF = ΔE − TΔS; domain walls form if ΔF < 0
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Area in space and time an agent can survey to find alternative paths to a goal; increases with collective size.
- Theoretical framework extending Yard-Sale model to characterize phase transitions in wealth dynamics under economic growth.
- Biologically plausible approximation lying between mean-field and Bethe approximations.
- Free energy approximation using two-node marginals.
- Perception that is smooth and can be evaluated at any point, like a differentiable field; Antra's functionalist interpretation.
- Model introduced in Figure 2 explaining how collective intelligence expands the spatiotemporal perceptual field of a group beyond any individual member's capacity.
- Approximations and prunings compose badly; cleaner to maintain precise infinite semantics until final extraction
- Factorised distribution used to approximate the true Bayesian posterior.