26 lessons in Machine Learning: The Whole Game

A rule found from examplesPredicting a numberHow the computer improves a guessChange one thingTelling two kinds apartHold some backWhen a model memorisesCounting mistakes honestlyHow a chatbot writesWhy a chatbot makes things upBeat the lazy guessChoosing what to measureMore data or a better modelTrain on one kind, test on anotherA third pile for choosingPeeking at the answersMoving the cut-offA model that keeps its examplesGoing together is not causingA model does not learn from youWho is in the dataWhen not to use a modelOne run is not proofThe whole workflowReading a claim about AIWhat a trained model is made of

Built to be understood — and remembered.

Every idea is taught with motivation and a worked example before the drills, and an FSRS spaced-repetition engine schedules each review for the day its model predicts you would forget it. A short placement check finds what you already know, so you start Machine Learning: The Whole Game exactly where it's useful.

Start Machine Learning: The Whole Game →

Related Ml subjects

Machine Learning: Learning from Data, in Code Machine Learning: Neural Networks from Scratch Machine Learning: Build Your Own Language Model Machine Learning: Deep Learning, Seeing and Remembering Machine Learning: Doing It Honestly