Skip to content

Machine Learning

Algorithms that improve at a task by learning patterns from data instead of being explicitly programmed.

Normally, to make a computer do something, a person writes exact rules: step 1, step 2, step 3. Machine learning flips this around. Instead of writing the rules yourself, you show the computer many examples and let it find the pattern on its own.

Think about learning to shoot free throws in basketball. Nobody hands you a math formula. You just take shot after shot, notice what works, and slowly get better. A machine learns the same way from examples: it makes a guess, checks how wrong it was, and adjusts.

The examples are called training data. The more examples you give it, and the better and cleaner those examples are, the better its predictions become. Give it messy or too few examples, and it stays clumsy. That is the whole idea behind ML.

The main ideas

  • Supervised learning — Learn a mapping from inputs to labelled outputs — classification and regression.
  • Unsupervised learning — Find structure in unlabelled data — clustering, dimensionality reduction, density estimation.
  • Self-supervised learning — Create supervision from the data itself (e.g. predict the next token); the engine behind modern foundation models.
  • Reinforcement learning — Learn by trial and error from rewards; covered in depth in its own area.
  • Core algorithms — Linear/logistic regression, decision trees, SVMs, k-NN, naive Bayes, and ensembles like random forests and gradient boosting.
  • Feature engineering — Turning raw data into informative inputs — scaling, encoding, selection, and extraction.
  • Training & evaluation — Loss functions, gradient descent, regularization, cross-validation, and the bias–variance / over- vs under-fitting trade-off.

Foundations of AI · Deep Learning · Data & MLOps

Want to make things?

Head to AI School — AI camps where kids build their own games.