- Course
- AI
Model Evaluation with Amazon SageMaker
Machine learning models need to be high performing and able to generalize new data. Evaluating these models checks how capable they are of doing just that. This course will teach you how to evaluate machine learning models with Amazon SageMaker.
What you'll learn
Having and maintaining high performing machine learning models is the key to having successful AI solutions. In this course, Model Evaluation with Amazon SageMaker, you’ll learn to assess the performance of machine learning models. First, you’ll explore how to evaluate models using SageMaker Canvas, focussing on the key metrics.. Next, you’ll discover how to do a similar evaluation with the Python SDK for model evaluation. Finally, you’ll learn how to identify model drift and apply best practices for continuous performance improvement of your machine learning models.
When you’re finished with this course, you’ll have the skills and knowledge of model evaluation needed to make sure that your models are, and remain, effective in various AI applications.
Table of contents
About the author
Maaike is trainer and software developer. She has trained professionals in the field of Java, Spring, C#, Python, Scrum, React and Angular. Next to the practical training and programming experience, Maaike has a lot of experience with short technical consulting projects and providing learning solutions for complex software development departments.