All topic hubs

Beginner learning hub

Machine Learning Foundations

Machine learning foundations connect a decision to data, a measurable target, a baseline, a trained model, protected evaluation, and an operational decision. Learning algorithms without this complete workflow makes it difficult to tell whether a model is useful or merely complex.

Best for: Beginners and software developers starting applied machine learning

Recommended learning order

  1. 1AI & ML OrientationWhat AI and ML are, how learning differs from rules, and how to choose a first path.Open lesson
  2. 2Python & NumPy for MLWrite small Python programs and reason about arrays, shapes, vectorization, and reproducible experiments.Open lesson
  3. 3Data Exploration & PreprocessingInspect real data, handle missing values, encode features, avoid leakage, and build repeatable transformations.Open lesson
  4. 4ML Workflow & EvaluationFrame a problem, split data correctly, choose metrics, detect overfitting, and compare against a baseline.Open lesson
  5. 5Linear RegressionPredicting continuous values using a linear relationship.Open lesson
  6. 6Logistic RegressionBuild an interpretable binary classifier using logits, sigmoid probabilities, cross-entropy, and thresholds.Open lesson
  7. 7Responsible AI FoundationsTranslate fairness, privacy, safety, transparency, and human oversight into testable design decisions.Open lesson

Decisions this path should help you make

  • When should a problem use deterministic rules instead of ML?
  • Which split reproduces the deployment boundary?
  • Which metric and threshold represent the real error costs?
  • What evidence is required before a limited launch?
Updated August 27, 2026 · Free public lessons · No login required