Ml

Learn Machine Learning: Learning from Data, in Code

Write the models of the first chapter yourself in Python: load the penguins, measure the error, work out its slope, and train with a loop you wrote.

Start Machine Learning: Learning from Data, in Code free → Browse all subjects

Free to start · adaptive placement finds your level · reviews timed to your own forgetting.

26 lessons in Machine Learning: Learning from Data, in Code

Penguins in PythonA model is a functionMeasuring the missWhich way is downhill?The slope, worked out exactlyThe training loopScale the inputs firstMany inputs at onceA score into a chanceSurprise as the errorTraining a classifierFrom chances to answersPrecision and recallHold some back, in codeFive foldsWords as columnsA penalty for big weightsCatch the leakMissing measurementsA tree of questionsMany trees, one voteFast code for every stepFive seeds, one reportThe whole pipelineWhich model for which job?A neuron, already built

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: Learning from Data, in Code exactly where it's useful.

Start Machine Learning: Learning from Data, in Code →
Related Ml subjects
Machine Learning: The Whole GameMachine Learning: Neural Networks from ScratchMachine Learning: Build Your Own Language ModelMachine Learning: Deep Learning, Seeing and RememberingMachine Learning: Doing It Honestly