Harvard's CS50 AI: search, knowledge, uncertainty, optimisation, learning, neural networks and language, through Python projects.
From the team behind Harvard's famous CS50, this course explores the ideas and algorithms at the foundation of modern AI — from search and logic to probability, machine learning and neural networks — with a hands-on Python project for each topic. The materials are free online.
glitchdata links to this course; its content, schedule and pricing are set by Harvard University.
This course is run by Harvard University. glitchdata describes it and links to it, but doesn't host its lessons — you take it on their site, under their terms.
cs50.harvard.edu ↗2 min read
2 min read
2 min read
2 min read
Turning things into numbers that carry meaning, and what you can do with them.
Attention, tokens and the architecture behind current language models — enough to reason about behaviour.
Model, parameter, inference, context, temperature — the terms, used correctly.