Representational Divergence

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

• Representational Convergenceconcept0.844
  The central empirical phenomenon: different neural networks trained on different data/objectives develop increasingly similar representations
• KL Divergenceconcept0.809
  A measure of the difference between two probability distributions, used extensively in free energy formulations.
• representational driftconcept0.809
  Accumulation of mismatch in later layers causing S degradation.
• Pernicious Divergenceconcept0.808
  Divergences that activate hidden pathways or cause dormant behavioral changes, undermining mechanistic claims
• Harmless Divergenceconcept0.803
  Divergences that occur in the behavioral null-space and do not affect functional claims about the model
• Representational divergence (as measured by EMD) can predict lower out-of-distribution intervention performanceclaim0.799
  Practical utility of reducing divergence demonstrated through regression analysis
• Representational Disentanglementconcept0.794
  CIMC's characterization of part of the solution to the Hard Problem: insight into the structural necessities of phenomenal representation
• What has led to representational convergence, will it continue, and ultimately where does it end?question0.790
  Central motivating questions of the paper