Loading page
Computer science
Learn the workflow from a measurable question to a tested model and honest conclusion.
features = [[0], [1], [2]]
labels = [0, 1, 1]
# Split, train, evaluate, and explain.COURSE CURRICULUM
Finish one section at a time or jump directly to a concept you need.
Learn how machine-learning questions, baselines, and measurable outcomes works in Machine Learning, why the underlying model matters, and how to apply it in a small program without hiding important trade-offs.
Learn how features, labels, datasets, and experiment structure works in Machine Learning, why the underlying model matters, and how to apply it in a small program without hiding important trade-offs.
Learn how parameters, hyperparameters, state, and reproducibility works in Machine Learning, why the underlying model matters, and how to apply it in a small program without hiding important trade-offs.
Learn how numeric, categorical, text, image, and missing inputs works in Machine Learning, why the underlying model matters, and how to apply it in a small program without hiding important trade-offs.
Learn how losses, gradients, regularization, and optimization works in Machine Learning, why the underlying model matters, and how to apply it in a small program without hiding important trade-offs.
Learn how decision boundaries, thresholds, and calibration works in Machine Learning, why the underlying model matters, and how to apply it in a small program without hiding important trade-offs.
Learn how training loops, batching, epochs, and convergence works in Machine Learning, why the underlying model matters, and how to apply it in a small program without hiding important trade-offs.
Learn how models, pipelines, feature transforms, and reuse works in Machine Learning, why the underlying model matters, and how to apply it in a small program without hiding important trade-offs.
Learn how train, validation, test sets, and grouped data works in Machine Learning, why the underlying model matters, and how to apply it in a small program without hiding important trade-offs.
Learn how text, embeddings, categorical encoding, and scaling works in Machine Learning, why the underlying model matters, and how to apply it in a small program without hiding important trade-offs.
Learn how leakage, imbalance, drift, and failure analysis works in Machine Learning, why the underlying model matters, and how to apply it in a small program without hiding important trade-offs.
Learn how experiment tracking, model versions, and deployment boundaries works in Machine Learning, why the underlying model matters, and how to apply it in a small program without hiding important trade-offs.
Learn how linear models, trees, ensembles, and neural networks works in Machine Learning, why the underlying model matters, and how to apply it in a small program without hiding important trade-offs.
Learn how data loading, inference, serving, and monitoring works in Machine Learning, why the underlying model matters, and how to apply it in a small program without hiding important trade-offs.
Learn how cross-validation, metrics, robustness, and fairness tests works in Machine Learning, why the underlying model matters, and how to apply it in a small program without hiding important trade-offs.