Dirichlet Distribution

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Dirichlet Parameter Accumulationmethod0.803
  Learning rule for updating Dirichlet beliefs about likelihood matrix A by adding outer products of observations and state estimates.
• Preferred Distributionconcept0.745
  In active inference, the distribution over goal states; here replaced by the learned self-prior rather than a hand-specified prior
• Categorical Distributionconcept0.745
  Probability distribution over discrete states or outcomes.
• Digit-token logit distributionconcept0.727
  Full distribution over tokens 0-9 at first generation step; contains more information than any single sampled token
• Natural Distribution of Representationsconcept0.725
  The distribution of latent representations produced by the model under unperturbed inputs
• Distributed/distributable and dynamic selfconcept0.709
  Concept of self as extended and co-constituted by interactions, per Mahāyāna.
• Even Distribution of Onsetsconcept0.707
• Out-of-Distribution (OOD) Generalizationconcept0.704
  Machine learning generalization when training and test distributions differ; linked to causal invariance.