Automated Machine Learning in Action

5 Customizing the search space by creating AutoML pipelines

This chapter covers

• Understanding an AutoML pipeline
• Customizing sequential and graph-structured AutoML pipelines
• Automated hyperparameter tuning and model selection with customized AutoML pipelines
• Customizing the AutoML blocks in the AutoML pipeline

In chapter 4, we solved a variety of problems with AutoKeras without customizing the search space. To recap, in AutoML, a search space is a pool of models with specific hyperparameter values that potentially can be built and selected by the tuning algorithm. In practice, you may want to use a specific ML algorithm or data preprocessing method to solve a problem, such as an MLP for a regression task. Designing and tuning a particular ML ...