Writing *Why Machines Learn* led to a 10-day ML course at IIT Madras
DSaience · x · 2026-07-27
Writing WHY MACHINES LEARN led to an unexpected payoff: the author returned to IIT Madras, decades after graduating, to teach a 10-day Intro to ML/AI course for PhD and master’s students at the Wadhwani School of Data Science and AI.
The course ran from 10 AM to 5 PM most days and covered the history of machine learning plus core math and methods: perceptron convergence, LMS, MLE/MAP, SVMs, kernel methods, backpropagation, GANs, VAEs, diffusion models, CNNs, transformers, and LLMs. It closed with a discussion of how deep learning has complicated statistical learning theory, including double descent and grokking.
More from Companies & People
- AMD and South Korea Partner on Heterogeneous Computing and Local NPU R&D — JungWooHa2 · 2026-07-27
- Alibaba says RecGPT-V3 cuts serving cost 52.4% while lifting Taobao GMV 3.97% — burny_tech · 2026-07-27
- NVIDIA and dozens of firms back a letter arguing open frontier models matter — ying11231 · 2026-07-27
- Stanford AI Lab cites NVIDIA’s Alpamayo platform as a model for open Physical AI — StanfordAILab · 2026-07-27
- Ben Lang’s 90-day X follower growth ranking spotlights AI startups across models, infra and apps — FinanceYF5 · 2026-07-27
- AI may automate the pipeline that creates experts before it automates experts themselves — imjustnewatai · 2026-07-27