Maybe I was too harsh on deep learning theory (three days ago) — LessWrong
A few days ago, I reviewed a paper titled “There Will Be a Scientific Theory of Deep Learning". In it, I expressed appreciation for the authors for w…
x Maybe I was too harsh on deep learning theory (three days ago) — LessWrong AI World Modeling Frontpage 2026 Top Fifty: 11 % 109 Maybe I was too harsh on deep learning theory (three days ago) by LawrenceC 30th Apr 2026 5 min read 13 109 A few days ago, I reviewed a paper titled “There Will Be a Scientific Theory of Deep Learning" . In it, I expressed appreciation for the authors for writing the piece, but skepticism for stronger forms of their titular claims. Since then I’ve spoken with various past collaborators (via text and in person), and read or reread quite a few deep learning theory pa
Explore this link on the map →saved by
related reading
- The paper that killed deep learning theory — LessWronglesswrong.com
- [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
- [2503.02113] Deep Learning is Not So Mysterious or Differentarxiv.org
- A Theory of Deep Learning | Elements of a Vector Spaceelonlit.com
- Growth and Form in a Toy Model of Superposition — LessWronglesswrong.com
- Deep learning as program synthesis — LessWronglesswrong.com
- Timaeus | Learn about SLTtimaeus.co
- The Scaling Hypothesis · Gwern.netgwern.net
- arxiv.org/pdf/1805.08522arxiv.org
- Neural networks generalize because of this one weird trick — LessWronglesswrong.com
- Greg Yang | Professional pagethegregyang.com
- SLT for AI Safety — LessWronglesswrong.com