Course Modules
Module 1: Introduction to Machine Learning and Data Analytics
- Overview of Machine Learning (ML) on AWS
- Key components of AWS ML services
- Introduction to AWS data analytics tools (e.g., Amazon S3, Redshift, etc.)
Module 2: Preparing Data for ML
- Data pre-processing for machine learning models
- Using AWS Glue for ETL operations
- Structuring and organizing data in Amazon S3 for ML workflows
Module 3: Building and Training Machine Learning Models
- Introduction to Amazon SageMaker for model building
- Data labeling and feature engineering
- Training models using SageMaker built-in algorithms and custom models
Module 4: Model Evaluation and Hyperparameter Tuning
- Evaluating machine learning models using validation datasets
- Hyperparameter optimization with Amazon SageMaker
- Using SageMaker automatic model tuning for improving performance
Module 5: Deploying and Monitoring Machine Learning Models
- Deploying models to production using SageMaker endpoints
- Monitoring models in production with SageMaker Model Monitor
- Managing version control and rollback strategies
Module 6: Data Analytics Integration
- Integrating ML models with AWS data analytics tools (Redshift, QuickSight, etc.)
- Using AWS Lambda for event-driven model inference
- Real-time and batch processing analytics with SageMaker and Kinesis
Module 7: Advanced Machine Learning Topics
- Introduction to deep learning and neural networks
- Amazon SageMaker for deep learning workflows
- Using AWS AI services (e.g., Comprehend, Rekognition, etc.) for specialized ML tasks
