📊 Self-paced course
The statistics you actually need to build, evaluate, and reason about AI, generative models, and LLMs — grounded in AI examples throughout, not dice and coins.
The tour before the road trip: where statistics actually shows up when you build, train, and evaluate AI systems — no math yet, just the map.
The four numbers you compute first on any dataset — and why AI datasets lie to you if you only look at one of them.
Reasoning over outcomes you haven't seen yet — the math every classifier, spam filter, and hallucination detector runs on.
Four named shapes of uncertainty — and the one that's quietly running every single token your LLM ever generates.
You never have all the data. Here's the math for how much that should worry you — and how models turn a pile of observations into a fitted distribution.
Two variables that move together, a line that summarizes the pattern, and the realization that fitting that line is a miniature version of training.
The three quantities that measure "how surprised" a model is — and the actual loss function running underneath every LLM's training loop.
What actually happens when a model tries to shrink its loss over millions of steps — and the two ways that process quietly goes wrong.
You built a model. Now: is it actually good, or does it just look good on the one number you checked?
Where it all converges: perplexity, sampling and temperature, calibration, and the statistical shape of hallucination.
40 flashcards — four per lesson, written for active recall rather than definition-matching. Anki-importable, readable as plain Markdown either way.
A memory map — a 54-node JSON Canvas laying out how the ten lessons connect. Renders in Obsidian.
See the README for how to use each.