Building powerful machine learning models depends heavily on the set of hyperparameters used. But with increasingly complex models with lots of options, how do you efficiently find the best settings for your particular problem? In this course you will get practical experience in using some common methodologies for automated hyperparameter tuning in Python using Scikit Learn. These include Grid Search, Random Search & advanced optimization methodologies including Bayesian & Genetic algorithms . You will use a dataset predicting credit card defaults as you build skills to dramatically increase the efficiency and effectiveness of your machine learning model building.
Hyperparameters and ParametersFree
In this introductory chapter you will learn the difference between hyperparameters and parameters. You will practice extracting and analyzing parameters, setting hyperparameter values for several popular machine learning algorithms. Along the way you will learn some best practice tips & tricks for choosing which hyperparameters to tune and what values to set & build learning curves to analyze your hyperparameter choices.Introduction & 'Parameters'50 xpParameters in Logistic Regression50 xpExtracting a Logistic Regression parameter100 xpExtracting a Random Forest parameter100 xpIntroducing Hyperparameters50 xpHyperparameters in Random Forests50 xpExploring Random Forest Hyperparameters100 xpHyperparameters of KNN100 xpSetting & Analyzing Hyperparameter Values50 xpAutomating Hyperparameter Choice100 xpBuilding Learning Curves100 xp
This chapter introduces you to a popular automated hyperparameter tuning methodology called Grid Search. You will learn what it is, how it works and practice undertaking a Grid Search using Scikit Learn. You will then learn how to analyze the output of a Grid Search & gain practical experience doing this.Introducing Grid Search50 xpBuild Grid Search functions100 xpIteratively tune multiple hyperparameters100 xpHow Many Models?50 xpGrid Search with Scikit Learn50 xpGridSearchCV inputs50 xpGridSearchCV with Scikit Learn100 xpUnderstanding a grid search output50 xpUsing the best outputs50 xpExploring the grid search results100 xpAnalyzing the best results100 xpUsing the best results100 xp
In this chapter you will be introduced to another popular automated hyperparameter tuning methodology called Random Search. You will learn what it is, how it works and importantly how it differs from grid search. You will learn some advantages and disadvantages of this method and when to choose this method compared to Grid Search. You will practice undertaking a Random Search with Scikit Learn as well as visualizing & interpreting the output.Introducing Random Search50 xpRandomly Sample Hyperparameters100 xpRandomly Search with Random Forest100 xpVisualizing a Random Search100 xpRandom Search in Scikit Learn50 xpRandomSearchCV inputs50 xpThe RandomizedSearchCV Object100 xpRandomSearchCV in Scikit Learn100 xpComparing Grid and Random Search50 xpComparing Random & Grid Search50 xpGrid and Random Search Side by Side100 xp
In this final chapter you will be given a taste of more advanced hyperparameter tuning methodologies known as ''informed search''. This includes a methodology known as Coarse To Fine as well as Bayesian & Genetic hyperparameter tuning algorithms. You will learn how informed search differs from uninformed search and gain practical skills with each of the mentioned methodologies, comparing and contrasting them as you go.Informed Search: Coarse to Fine50 xpVisualizing Coarse to Fine100 xpCoarse to Fine Iterations100 xpInformed Search: Bayesian Statistics50 xpBayes Rule in Python100 xpBayesian Hyperparameter tuning with Hyperopt100 xpInformed Search: Genetic Algorithms50 xpGenetic Hyperparameter Tuning with TPOT100 xpAnalysing TPOT's stability100 xpCongratulations!50 xp
DatasetsCredit Card Defaults
PrerequisitesSupervised Learning with scikit-learn
Alex ScrivenSee More
Senior Data Scientist @ Atlassian
Alex is a Senior Data Scientist working for Atlassian in Sydney, Australia and has previous experience in government, agency and startup. He also holds lecturing and research positions at the University of Technology Sydney and the University of New South Wales. He has built and delivered several Masters-level courses in machine learning & deep learning whilst researching on applications of machine learning & data science in industry. From a heavily commercial background, Alex greatly enjoys bridging the gap between cutting-edge technology and business applications.