Maximal Marginal Relevance

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

• Optimal Data Selectionconcept0.734
  Question of how rationally agents query the world; subsumed by expected free energy minimization
• maximum-norm gradient normalizationmethod0.719
  Training-free technique normalizing all task gradients to the maximum gradient norm magnitude
• Linear representationconcept0.716
  The idea that features are encoded as directions in activation space.
• log-evidence (marginal likelihood)concept0.713
  Model evidence approximated by free energy bound, used for model selection.
• Maximum gradient norm scalingconcept0.704
  Scaling aggregated gradient by the maximum gradient norm among tasks.
• Marginaliaconcept0.703
  Secondary texts placed in margins that contest, complicate, and intervene in the primary text, creating pressure points and alternative discourse.
• Maximum Margin Separatorconcept0.702
  The direction logistic regression converges to on linearly separable data; shown to be suboptimal for identifying truth direction
• Medium-term memoryconcept0.699
  Vascular clamp's function: holding specific predictions stable over timescales longer than working memory.