Evaluating foundation model output

AIF-C01 · Applications of Foundation Models · Updated

ROUGE, BLEU, BERTScore, benchmark datasets, human evaluation and business metrics, and how Amazon Bedrock model evaluation works.

This lesson is part of full AIF-C01 access

The first 2 AIF-C01 lessons are free. Full access opens every lesson with its practice questions, and the exam-style AIF-C01 question bank.

In this lesson
  • Automatic metrics
  • Amazon Bedrock model evaluation
  • Choosing a model
  • Business metrics
  • Exam traps
  • Practice questions

Get full access Try the free practice exam Log in

AIF-C01 course outline

All 8 lessons · Course overview
  1. ML learning types, tasks and metricsFundamentals of AI and ML Free
  2. AWS AI services and SageMaker AI toolsFundamentals of AI and ML Free
  3. Generative AI, LLMs and inference parametersFundamentals of Generative AI Full access
  4. Amazon Bedrock, Amazon Q and model customizationFundamentals of Generative AI Full access
  5. Prompt engineering techniquesApplications of Foundation Models Full access
  6. Evaluating foundation model outputApplications of Foundation Models Full access
  7. Responsible AI principles and toolsGuidelines for Responsible AI Full access
  8. Securing AI workloads and AWS compliance toolsSecurity, Compliance, and Governance for AI Solutions Full access