AI Engineer L6 M4 Practise Stage Lab Workshop 4

Lab for Workshop 4: Hyperparameter Tuning and Performance Optimisation

Description

Finding the best set of hyperparameters is essential to achieve the best performance from a model and this is what the lab explores. You will look at the process of finding the best model starting from establishing training, validation and testing data sets, types of cross validation, and then moving on to the hyperparameter optimisation problem and the different ways of formulating and solving it.

The lab is a sandbox allowing learners to examine and run available Jupyter notebooks, and to create their own based on tasks given to them. This lab environment holds datasets (csv files), Jupyter notebook, and instructions. It allows you to download your work to your computer.

Learning objectives

Upon completion of this intermediate lab, you will be able to:

• Increase model accuracy
• Reduce bias or variance
• Prevent overfitting or underfitting

Intended audience

• Data Engineers
• DevOps Engineers
• Machine Learning Engineers
• Software Engineers

Prerequisites

Familiarity with the following will be beneficial but is not required:

• Understanding of ML models
• ML Libraries & Tools such as scikit-learn, Optuna
• Python