Deep Learning Course Adds Mechanistic Interpretability Lecture This Winter
CSProfKGD · x · 2026-10-26
CSProfKGD, author of the EECS 6322 deep learning course "A Visual and Technical Journey Into Deep Learning," announced a new Mechanistic Interpretability lecture arriving this winter, with a trailer released.
- The course spans neural networks, transformers, diffusion models, and modern AI systems, combining visual intuition, math foundations, and hands-on implementation.
- Prerequisites are Python, calculus, linear algebra, and basic ML; essentials are reviewed along the way.
- Current videos are slide animations only; fully narrated lectures are coming soon, alongside curated textbooks and resources.
More from Companies & People
- Model PMs earn 60% more: median base pay hits $345K, analysis of 316 profiles shows — aakashgupta · 2026-10-26
- Google community talks don't need all-Google stacks: Next.js on Firebase counts — weskambale · 2026-10-26
- Anthropic has raised $141.1B to date, with $112.4B cash plus $19.3B short-term investments — citrini · 2026-10-26
- Patrick Collison: every decade had a reason not to start a company — all were great times — aldeamartinez · 2026-10-26
- Groupthink, not models, is quietly killing enterprise AI ROI, veteran architect warns — DavidLinthicum · 2026-10-26
- Anthropic delayed pre-training of a new frontier model for over a month over security concerns — scaling01 · 2026-10-26