Machine Learning (ML) · Intermediate level

Intermediate level · Module 3 of 6 · 13 guided hours

Hyperparameter Tuning

Search for good model settings efficiently and honestly, and use learning curves to decide whether more data or a different model would help.

Learning objectives

  • Tune hyperparameters with grid and random search
  • Avoid overfitting the validation process
  • Use learning curves to guide next steps

Topics

  • parameters vs hyperparameters
  • GridSearchCV
  • RandomizedSearchCV
  • nested cross-validation
  • learning curves
  • tuning budgets on slow hardware

Lessons

  1. Lesson 1 Grid and Random Search

    Tune hyperparameters systematically with cross-validated grid and random search.

    hyperparameterGridSearchCVRandomizedSearchCVstep__param naming

  2. Lesson 2 Honest Estimates after Tuning

    Keep performance estimates honest when tuning, using a held-out test set or nested cross-validation.

    optimistic biasnested cross-validationheld-out test setreporting

  3. Lesson 3 Learning Curves

    Use learning and validation curves to decide whether to collect more data, add features or change the model.

    learning curvevalidation curvehigh bias vs high variancevalue of more data

Practical activity

Tune the chosen agent model with randomised search inside the pipeline, record the search and evaluate the final model once on the test set.

Expected outcomes

  • Better-tuned models with honest estimates
  • Evidence-based next steps

Assessment

Tuning notebook marked on search design, absence of test-set leakage and interpretation.

Taught live by an instructor — online or in person. Free course lessons are for self-study and do not lead to a certificate — see registration options.