concept
active
concept:sensory-inputsensory input
Input from environment that the agent models and predicts.
Neighborhood — ranked by edge-count
Claims (1)
claim
- Redefines value in probabilistic terms, linking to surprise minimisation.
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.
- Assumption that DNN layers preserve input information by being injective; key condition for Theorem 1
- Redefinition of value in probabilistic terms.
- Correctness of input statements to an LLM, as opposed to output-truth (correctness of model-generated outputs).
- Sensory input providing evidence that is integrated with priors.
- Equated with inference of past, present and future hidden states via minimization of variational free energy.
- The mechanism by which each step's effect is evaluated against the life of the whole, guiding the unfolding.