Gregory Friedman The Greg Wide Web on the name →

The Lectures

Lectures

I want to be a professor; this is the practice, continued from two years of TA'ing (Data Structures, then the graduate machine-learning course) and Q-Center math tutoring. Each lecture takes one classic idea and does it in full: the mathematics derived, the code written from scratch, and an interactive plate so you can push on the ideas yourself.

Course I

Machine Learning

One classic algorithm per lecture, and each one gets three treatments: the mathematics, derived rather than asserted, with every update rule earned from a loss function and the chain rule; the implementation, in plain Python, structured so that each line of code answers to a line of the derivation; and an interactive plate to descend, train, or break. The code is pyml, no frameworks anywhere, and an algorithm ships only when its lecture does.

The full arc →

Course II

Data Structures & Algorithms

The course I TA'd at UConn (CSE 2050), retaught in Python after Sheehy's A First Course on Data Structures: ADTs as contracts, implementations tested against them, and analysis grounded in measurement. Fourteen lectures surveyed, each with a planned interactive plate, from a call-stack animation to Dijkstra running over a real map.

The full arc →

Keys on this page

A figure's keys are its own: they answer once the figure has focus, so tab to it or click it first. Esc closes this sheet.