What you'll learn

Real-world data is messy, and it is often difficult or costly to get labelled datasets. In this course, Building Systems with Unsupervised Learning, you’ll gain the ability to build and deploy intelligent systems that don't rely on labeled data. First, you’ll explore representation learning and autoencoders to create dense embeddings. Next, you’ll discover how to implement scalable vector search and similarity systems using vector databases. Finally, you’ll learn how to operate these unsupervised pipelines in production, managing challenges like data drift and embedding staleness. When you’re finished with this course, you’ll have the skills needed to design, build, and monitor sophisticated ML systems that leverage the full potential of unsupervised data.