concept
active
concept:representational-convergence

Representational Convergence

The central empirical phenomenon: different neural networks trained on different data/objectives develop increasingly similar representations

Neighborhood — ranked by edge-count

Thinkers (1)

thinker

Concepts (5)

concept
  • Measure of similarity between the similarity structures (kernels) induced by two different representations
  • Hypothesis that all well-performing neural nets represent the world in the same way; PRH extends this by specifying what representation they converge to
  • The tendency of deep networks to implicitly favor simpler solutions that fit the data, driving convergence
  • The pressure on models trained on more tasks to find representations that generalize across all tasks, reducing the solution space
  • Researcher preferences and goals of mimicking human reasoning shape model development, potentially causing convergence toward human-like representations

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.