Optimizing Foundation Models

In this course, you will explore two techniques to improve the performance of a foundation model (FM): Retrieval Augmented Generation (RAG) and fine-tuning. You will learn about Amazon Web Services (AWS) services that help store embeddings with vector databases, the role of agents in multi-step tasks, define methods for fine-tuning an FM, how to prepare data for fine-tuning, and more.

This course is intended for the following:

• Individuals interested in artificial intelligence and machine learning (AI/ML), independent of a specific job role

Optimizing Foundation Models is part of a series that facilitates a foundation on artificial intelligence, machine learning, and generative AI. If you have not done so already, it is recommended that you complete these two courses:

• Fundamentals of Machine Learning and Artificial Intelligence
• Exploring Artificial Intelligence Use Cases and Applications

In this course, you will learn how to do the following:

• Identify AWS services that help store embeddings with vector databases.
• Understand the role of agents in multi-step tasks.
• Understand approaches to evaluate FM performance.
• Determine whether an FM effectively meets business objectives.
• Define methods for fine-tuning an FM.
• Describe how to prepare data to fine-tune an FM.
• Determine whether an FM effectively meets the business objectives based on the business metric identified in the use case.