concept
active
concept:neural-collapse

Neural Collapse

Terminal phase phenomenon in deep learning training relevant to convergence of representations

Neighborhood — ranked by edge-count

Papers (1)

paper

Concepts (1)

concept
  • Input-Injectivity
    contradicts
    Assumption that DNN layers preserve input information by being injective; key condition for Theorem 1

Related by similarity (8)

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.

  • Neural Criticalityconcept0.785
    Threshold between ordered and chaotic dynamics; predicted to be more prevalent in post-dual agents due to lower VFE
  • Neural codeconcept0.784
    The model's parameters considered as the actual 'code' implementing its algorithms, as opposed to human-written code.
  • neural cognitionconcept0.770
    Cognition in nervous systems, used as a modelling target
  • Neural Annealingframework0.770
    Michael Johnson's prior work on how neural networks (and brains) can be 'annealed' to find optimal states.
  • neural substratesconcept0.769
    Brain-based physical implementations of consciousness-related functions, assumed by many ToCs to be exclusive.
  • Neural Networksconcept0.765
  • Neural Decodingframework0.762
  • Neuroscienceinstitute0.761