Learning On The Hypersphere: The Multi-Geometric Neural Network

Поделиться
HTML-код
  • Опубликовано: 2 фев 2025

Комментарии • 5

  • @beo-w
    @beo-w 3 часа назад

    🐐

  • @irbsurfer1585
    @irbsurfer1585 3 часа назад

    This appears to be a unique type of phase transition, distinct from standard grokking, but sharing some of its characteristics? A new kind of grokking specific to multi-geometry models, where spatial curvature acts as an implicit training signal? I think I really need to spend more time absorbing your ideas and brushing up on my hyperbolic geometry math. lol So just curvature differences, poincare disk model, and maybe just how trees and graphs fit with euculidean space? Or deeper still?

  • @davidjohnston855
    @davidjohnston855 Час назад

    What if you used your RL reasoning strategy to shape and optimize the layers? Or use your fibinacci strategy instead of backprop?

    • @richardaragon8471
      @richardaragon8471  Час назад

      I'll play around with this at some point in the future, I like it!

  • @carson1391
    @carson1391 2 часа назад +1

    thats hilarious if they sent this to you. they be watchin lol