Introduction
- Introduction
- Course Overview
- Why AWS AI Practitioner Certification and what is an AI Practitioner
- RegisteringTaking an exam for the first time What to know Demo
- AI Practitioner Exam Guide Exam Details and Domains
- Setting up your own AWS Account A walk through
Fundamentals of AI and ML
- Basic AI Concepts and Terminologies
- AI ML and Deep Learning Similarities and Differences
- Types of Inferencing
- Data Types in AI Models
- Supervised Unsupervised and Reinforcement Learning
- Identifying Practice Use cases for AIML
- ML Development Lifecycle and the ML Pipeline
- Introduction to MLOps concepts from design to metrics
- Overview of AI and ML Services on AWS
Fundamentals of Generative AI
- Basic Concepts of Generative AI tokens chunking embeddings and more
- Generative AI Use Cases and Applications
- Foundation Model Lifecycle
- Capabilities and Limitations of Generative AI Applications
- AWS Infrastructure for building Gen AI Applications
- Cost Consideration for AWS Gen AI Services redundancy availability performance and more
Applications of Foundation Models
- Design considerations for Foundation Model Applications
- Selecting Pre Trained Models
- Inference Parameters and their effects
- Retrieval Augmented Generation RAG and its uses
- Vector Databases on AWS
- Foundation Model Customization Approaches
- Agents for Multi step tasks
- Prompt Engineering Techniques and Best Practices
- Training and Fine tuning Process for Foundation Models
- Evaluating Foundation Model Performance
Guidelines for Responsible AI
- Features of Responsible AI
- Tools for Identifying Responsible AI Features
- Responsible Model Selection Practices
- Features of Responsible AI
- Legal Risks in Generative AI
- Dataset Characteristics and Bias
- Dataset Characteristics and Bias
- Transparent and Explainable Models
- Human centered Design for Explainable AI
Security, Compliance, and Governance for AI Solutions
- Securing AI Systems with AWS Services
- Source Citation and Data Lineage
- Best Practices for Secure Data Engineering
- Security and Privacy Considerations for AI Systems
- Regulatory Compliance Standards for AI Systems
- AWS Services for Governance and Compliance
- AI Data Governance Strategies