Waterloo deep learning theory lecture notes on neural network scaling limits released
thegautamkamath · x · 2026-09-09
mufanli (Waterloo) released lecture notes from a fall topics course on deep learning theory, written with help from GPT. The notes focus on scaling limits of neural networks, and the author welcomes comments and corrections. A solid free resource for anyone studying the theoretical foundations of scaling.
More from Research
- ELT poster at ECCV 2026: looped transformers for visual generation and stable training — adityakusupati · 2026-09-10
- Composing continual learning mechanisms lifts retention from 1.2% to 34.9% — DanielKhashabi · 2026-09-09
- 30 CLIP models, 40 datasets: bigger vision encoders aren't always better — KevinKaichuang · 2026-09-09
- Two PDE papers from DARPA's expMath collaboration with Eduardo Teixeira — srchvrs · 2026-09-09
- Math Bodies Must Decide What Counts as Proof as AI Slop Proofs Flood In — thebasepoint · 2026-09-09
- Phillip Isola: Computer Vision Should Become More Like Vision Science Now the Creature Exists — phillip_isola · 2026-09-09