paper
referenced-only
2018
paper:balestriero-2018-spline

A Spline Theory of Deep Learning

ByRandall Balestriero·Richard Baraniuk

Similar preprints — Semantic Scholar

Cited by (2)

  • Do Sparse Autoencoders Capture Concept Manifolds?

    Sparse autoencoders trained on Llama3.1-8B (layer 19, 500M Pile tokens, 25 SAEs across Standard, JumpReLU, TopK, BatchTopK and Matryoshka architectures at VE > 0.85) do not capture continuous concept

  • The Platonic Representation Hypothesis

    Neural networks trained on different data modalities, architectures, and objectives are converging toward a shared statistical model of reality — what the paper terms the "platonic representation" — f