Sasha Rush's Deep Learning Speedrun shows the minimal math to train MNIST
srush_nlp · x · 2026-10-29
Sasha Rush (co-author of the Transformer paper) answers his own question — what's the minimal amount of math you need to train an MNIST model? — pointing to his Deep Learning Speedrun tutorial as the answer. A streamlined path for readers wanting to get hands-on with training with minimal math background.
Related event: srush Derives MNIST from Peano Axioms in 3000 Lines of Lean(2 posts)→
More from Research
- AI-for-science benchmarking markets: single evals may cost months and millions, a durable niche — kenbwork · 2026-10-30
- pstack's /statechart skill ships with a mini TLC compiler that helped find real distributed-systems bugs — DavidKPiano · 2026-10-30
- Neural twins: models trained for each other, chatting in neuralese — repligate · 2026-10-30
- Self-Direction turns agent mistakes into LoRA lessons, lifting GAIA success from 38.8% to 55.8% — rohanpaul_ai · 2026-10-30
- Preprint: AlphaGenome pervasively underestimates causal variant effects, undermining fine-mapping — anshulkundaje · 2026-10-30
- One Researcher on 22 NeurIPS 2026 Papers: What Should Author Lists Mean? — qberthet · 2026-10-30