This course covers part of the model development phase of the machine learning (ML) lifecycle.
In this course, you will learn how to refine and customize models so that they generalize well and fit your business need. This course covers techniques to prevent overfitting, underfitting, and catastrophic forgetting, and how to combine models with ensemble methods such as boosting, bagging, and stacking.
For generative AI, you will work through the customization spectrum, from prompt engineering and retrieval augmented generation (RAG) to fine-tuning and model distillation with Amazon Bedrock, and learn to optimize the retrieval components of a RAG system.