Likelihood Array (A matrix)

High-dimensional array mapping hidden states to outcomes; key learned quantity in the paradigm

Neighborhood — ranked by edge-count

concept

Generative Model
associated_with
Agent's internal probabilistic model of environment; enables belief inference about hidden states given outcomes.
Concentration Parameters
associated_with
Sufficient statistics of Dirichlet priors over likelihood; accumulate as experience is gained; analogous to synaptic efficacy

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.

Copying Matrixconcept0.724
An OV circuit matrix that maps tokens to increasing the logit of those same tokens; detectable via positive eigenvalues
log-evidence (marginal likelihood)concept0.718
Model evidence approximated by free energy bound, used for model selection.
Rank-one matrixconcept0.707
The simple matrix form into which VPD constrains subcomponents to enforce mechanistic simplicity.
Message Passing Inferenceconcept0.704
Algorithmic framework for probabilistic inference in graphical models.
Learning the likelihood matrix A via Dirichlet parameter accumulation is formally identical to associative or Hebbian plasticity.claim0.696
Connection between learning rule and synaptic plasticity.
Multi Level Bayesian Inferenceframework0.691
Quantum Compositional AIconcept0.690
Integration of quantum mechanics with compositional AI principles; extends classical compositional reasoning to quantum domain.
Hard Inferenceconcept0.689
Post-training inference mode where each gate uses only its most probable discrete operation for fast binary execution