Hyperparameter Tuning with Grid Search, and Cross-Validation

Automating hyperparameter search with GridSearchCV over a real heatmap of (C, gamma) combinations, and why k-fold cross-validation gives a far more honest picture of a model's performance than one train/test split.

~7 min total·4 quadrants of structured content

By the end of this topic, you will

Run a GridSearchCV over an SVM's C and gamma hyperparameters and read the resulting heatmap
Explain why a single train/test split's accuracy number can mislead
Run 5-fold cross-validation and interpret both the mean and standard deviation it reports

Quadrant 1 · e-Tutorial

Video lectures and walkthroughs

Video content coming soon.

Quadrant 2 · e-Content

Articles and case studies

Hyperparameter Tuning with Grid Search, and Cross-Validation

Every classifier so far was trained with hyperparameters chosen by hand. GridSearchCV tries every combination and reports which one actually scored best, cross-validated.

Quadrant 3 · Web Resources