Lars Ruthotto's 10-lecture NSF CBMS course on Computational Math and AI, videos and slides free
caglar_ee · x · 2026-09-09
Emory professor Lars Ruthotto's ten-lecture NSF CBMS 2025 course on Computational Mathematics and AI (Dec 8–12, 2025, Houston) is now available as a full YouTube playlist with all slide PDFs. Topics span ML fundamentals (bias-variance, double descent), architectures and inductive biases, optimization theory and practice, why SGD works (implicit regularization, Langevin dynamics), adaptive methods (Adam/AdamW/Lion, K-FAC), PDE frameworks for generative modeling, scientific ML, high-dimensional PDEs, inverse problems, and AI-assisted mathematical discovery.
More from Research
- Shanghai AI Lab proposes first systematic taxonomy of cognition-induced AI agent risks — jiqizhixin · 2026-09-09
- Stu-tU: RANSAC scoring that survives 128x scale miscalibration — ducha_aiki · 2026-09-09
- Test-time compute could be 10,000 model instances coordinating on a message board — mertdumenci · 2026-09-09
- Do transformers lose object-like 'seeing' of definitions through training? — MoonL88537 · 2026-09-09
- Marigold V2 retools diffusion transformers for sharper monocular depth estimation — huawei-bayerlab · 2026-09-09
- kornia-rs: Rust Low-Level 3D Vision Library Outperforms OpenCV and NVIDIA VPI — edgarriba · 2026-09-09