concept
active
concept:actionaction
Changing configuration to sample environment differently; minimizes free energy.
Neighborhood — ranked by edge-count
Papers (1)
paper
Frameworks (1)
framework
- Free Energy Principleassociated_withA foundational variational principle from statistical physics that formalizes how self-organizing systems maintain structural integrity and adapt to their environment by minimizing free energy—a mathematical bound on surprise or prediction error. Originally developed by Karl Friston, the framework unifies action, perception, and learning as processes of active inference, where systems both update internal models of the world and act upon it to reduce the divergence between predictions and observations.
Claims (2)
claim
- Reinterprets classical reward/value concepts through free energy lens.
- Acting to optimize value and perception are two aspects of exactly the same principle: minimization of free energy.associated_withFoundational claim unifying action and perception within single optimization framework.
Events (1)
event
- First lecture of the series, introducing the free-energy principle and unification of action and perception.
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.
- Choice of policies minimizing expected free energy to realize preferred future states.
- Central explanatory target: behavior constrained by prior intentions and contextual constraints that emerge from cognitive reorganization.
- Dual interpretation of features: in addition to responding to inputs, features also act to increase probability of specific output tokens
- The ability of a collective to orchestrate behaviours of its parts towards system-level goals.
- Coordinated behavior of multiple components required to achieve non-linearly separable outcomes.
- Represented by boxes in process theory; transformations that take systems as inputs/outputs
- The continuous process of creating and strengthening living centers as the most essential aspect of unfolding.
- Internal representations of the model on which probes operate; the method uses activations to rank datapoints.