Why do we use the strange word "hyperparameter"? What makes it hyper? Here, you will understand what model parameters are, and why they are different from hyperparameters in machine learning. You will then see why we would want to tune them and how the default setting of caret automatically includes hyperparameter tuning.

Parameters vs hyperparameters

Model parameters vs. hyperparameters

Hyperparameters in linear models

What are the coefficients?

Recap of machine learning basics

Machine learning with caret

Resampling schemes

Hyperparameter tuning in caret

Hyperparameters in Stochastic Gradient Boosting

Changing the number of hyperparameters to tune

Tune hyperparameters manually

Introduction to hyperparameters

In this chapter, you will learn how to tune hyperparameters with a Cartesian grid. Then, you will implement faster and more efficient approaches. You will use Random Search and adaptive resampling to tune the parameter grid, in a way that concentrates on values in the neighborhood of the optimal settings. 

Finding hyperparameters

Cartesian grid search in caret

Plot hyperparameter model output

Grid vs. Random Search

Grid search with range of hyperparameters

Find train() option for random search

Random search with caret

Adaptive resampling

Advantages of Adaptive Resampling

Adaptive Resampling with caret

Hyperparameter tuning with caret

Here, you will use another package for machine learning that has very convenient hyperparameter tuning functions. You will define a Cartesian grid or perform Random Search, as well as advanced techniques. You will also learn different ways to plot and evaluate models with different hyperparameters.

Machine learning met mlr

Machine Learning met mlr

Modelleren met mlr

Grid- en random search met mlr

Random search met mlr

Voer hyperparameter-tuning uit met mlr

Hyperparameters evalueren met mlr

Waarom tuning evalueren?

Resultaten van hyperparameter-tuning evalueren

Geavanceerd tunen met mlr

Geavanceerde tuning-instellingen definiëren

Geaggregeerde metingen definiëren

Hyperparameters instellen

Hyperparameter tuning with mlr

In this final chapter, you will use h2o, another package for machine learning with very convenient hyperparameter tuning functions. You will use it to train different models and define a Cartesian grid. Then, You will implement a Random Search use stopping criteria. Finally, you will learn AutoML, an  h2o interface which allows for very fast and convenient model and hyperparameter tuning with just one function.

Machine learning with h2o

Prepare data for modelling with h2o

Modeling with h2o

Grid and random search with h2o

Grid search with h2o

Random search with h2o

Stopping criteria

Automatic machine learning with H2O

AutoML in h2o

Scoring the leaderboard

Extract h2o models and evaluate performance

Wrap-up

Hyperparameter tuning with h2o

Bc test data

Bc train data

Breast cancer data

Breast cancer data orig

Datasets descriptions

Knowledge data

Knowledge orig

Knowledge test data

Knowledge train data

Seeds data

Seeds dataset

Seeds test data

Seeds train data

Voters data

Voters orig

Voters test data

Voters train data

Voor veel Machine Learning-problemen is een model zomaar draaien en een voorspelling krijgen niet genoeg; je wilt het beste model met de meest nauwkeurige voorspelling. Een manier om je model te verbeteren is hyperparameterafstelling: het optimaliseren van de instellingen voor dat specifieke model. In deze cursus werk je met de pakketten caret, mlr en h2o om de optimale combinatie van hyperparameters te vinden, op een efficiënte manier met grid search, random search, adaptieve hersteekproeven en automatische Machine Learning (AutoML). Daarnaast werk je met verschillende gegevenssets en stem je verschillende supervised learning-modellen af, zoals random forests, gradient boosting machines, support vector machines en zelfs neurale netten. Klaar om te tunen!

Machine Learning with caret in R

Gebruik caret, mlr en h2o om optimale hyperparameters te vinden via grid search, random search en AutoML.

Hyperparameterafstelling in R

Leer hoe je de hyperparameters van je model kunt afstemmen om de beste voorspellingsresultaten te krijgen.

Wetenschapper op het gebied van machine learning in R

Begeleid machine learning in R

Waarom tuning evalueren?

Hyperparameterafstelling in R

Praktische interactieve oefening