Skip to content

Learn machine learning

Ten stops, in order: the eight topic planets from the home page plus two overviews. Start with data preparation on the left, then follow the lines: supervised learning above, unsupervised below, and the systems built on them to the right. Every page has a playground.

  1. 01 Data preparation

    Foundations

    Most of the work, and most of the mistakes, happen before any model is trained. How data is prepared for each kind of learning.

  2. 02 Supervised learning

    Supervised

    Learning a mapping from inputs to a known answer. Regression predicts numbers, classification predicts categories.

  3. 03 Regression

    Supervised

    Predicting a number. From a straight line to boosted trees, and how to tell a good fit from a memorised one.

  4. 04 Classification

    Supervised

    Predicting a category, and a probability for it. Decision boundaries, thresholds and metrics that survive imbalance.

  5. 05 Unsupervised learning

    Unsupervised

    Finding structure when nobody has labelled the data. Clustering groups rows, dimensionality reduction compresses columns.

  6. 06 Clustering

    Unsupervised

    Grouping points that belong together, without labels. Centroids, densities, mixtures and hierarchies.

  7. 07 Dimensionality reduction

    Unsupervised

    Squeezing many features into a few while keeping what matters, for plotting, compression and cleaner inputs.

  8. 08 Embeddings

    Representation

    Turning text into vectors so that similar meaning becomes small distance. The foundation of semantic search and RAG.

  9. 09 Retrieval-augmented generation

    Systems

    Giving a language model the right documents at the right moment: the full pipeline from ingestion to evaluation.

  10. 10 Recommender systems

    Systems

    Predicting what each person will want next, from what they and people like them did before.