This unit introduces core model concepts, operational practices, and governance needed to customize, deploy, and monitor AI systems on AWS. Students learn foundation model architectures, tokenization and embeddings, AWS AI services (including Bedrock and SageMaker), MLOps pipelines, and the security, ethical, and compliance considerations necessary for responsible deployment.
Learning Objectives
- Analyze the relationships among AI, machine learning, and deep learning and explain the transformer architecture and foundation models, including tokenization, chunking, and embeddings
- Apply AWS AI services (e.g., Amazon Bedrock and SageMaker) to customize models, configure inference parameters, and build knowledge bases that support targeted application scenarios
- Demonstrate MLOps pipeline components and workflows—such as model versioning, automated deployment, monitoring, and rollback—using AWS tools and best practices
- Evaluate security, governance, compliance, and ethical implications to identify unsuitable AI/ML use cases and recommend controls for responsible AI implementation in AWS environments
Curriculum
- 1 Section
- 14 Lessons
- 30 hours
Expand all sectionsCollapse all sections
- Unit 2 — Modeling, MLOps, and Responsible AI14
- 1.1Model Customization and Evaluation20 mins
- 1.2MLOps20 mins
- 1.3Implementing Responsible AI with AWS Services20 mins
- 1.4AI Security, Governance, and Compliance20 mins
- 1.5Diving Deeper into Terms You Should Know20 mins
- 1.6From Text to Numbers: Tokens, Chunking, and Embeddings20 mins
- 1.7Use Cases Unsuitable for AI and ML Applications20 mins
- 1.8AWS AI Services20 mins
- 1.9The Effect of Inference Parameters on Model Responses20 mins
- 1.10Amazon Bedrock Knowledge Bases20 mins
- 1.11MLOps Pipeline20 mins
- 1.12ML Governance with SageMaker AI20 mins
- 1.13The Relationship Among AI, ML, and Deep Learning20 mins
- 1.14The Transformer Architecture and Foundation Models20 mins
Instructor
Free
Leave a Reply