Part 2 AutoML in practice

 

The previous chapters provided a basic introduction to machine learning, different kinds of ML models, and the workflow of handling ML problems. You’ve also seen one of the most intuitive AutoML methods for hyperparameter tuning: using grid search to tune an ML pipeline with the help of the scikit-learn toolkit.

Starting with chapter 4, you learn how to address ML problems and improve ML solutions with AutoML. We focus mainly on generating deep learning solutions in the next two chapters, considering the prominence of deep learning models and how complicated it is to design and tune them. You will be able to create deep learning solutions for different ML tasks with the help of advanced AutoML toolkits: AutoKeras and KerasTuner. Chapter 6 introduces a general solution to customize the entire AutoML search space, giving you more flexibility in designing the search space for tuning unsupervised learning models and optimizing algorithms.