Glossary · Term

Attractor Model

← all terms

Definition

A model design that finds an answer by jumping straight to where its internal computation would settle, instead of iterating to get there.

An architecture that frames recurrent refinement as a fixed-point problem and uses implicit differentiation for constant-memory training, with the equilibrium living in output-embedding space.

Also called: Attractor Models

Mentioned in 1 episode

  1. 041
    When the Iteration Teaches the Model to Skip the Iteration