Machine Learning Pipeline on AWS

The Machine Learning Pipeline on AWS course offers an immersive project-based learning environment that explores the iterative process of building and deploying Machine Learning (ML) models to solve real business problems. Throughout the course, learners will gain a comprehensive understanding of each phase of the ML process pipeline through instructor presentations and demonstrations.

In this course, learners will have the opportunity to apply their knowledge to complete a project focused on solving one of three business problems: fraud detection, recommendation engines, or flight delays.

Through hands-on exercises and practical implementation, participants will develop skills in building, training, evaluating, tuning, and deploying ML models using Amazon SageMaker.

By the end of the course, students will successfully build, train, evaluate, tune, and deploy an ML model using Amazon SageMaker to address their selected business problem. This comprehensive project-based approach allows learners to gain practical experience and demonstrate their ability to apply ML techniques to real-world scenarios.

• Developers
• Solutions Architects
• Data Engineers
• Professionals wanting to learn about ML pipelines using Amazon SageMaker

• Familiarity with the Python programming language
• A fundamental knowledge of AWS Cloud infrastructure (Amazon S3 and Amazon CloudWatch)
• Basic experience working with Jupyter notebooks

• Gain a comprehensive understanding of the ML process pipeline and its different stages, from data preprocessing to model deployment
• Explore various data preprocessing techniques to clean, transform, and prepare data for training ML models
• Develop skills in feature engineering and selection to optimise model performance and interpretability
• Learn different ML algorithms and techniques applicable to the selected business problem, such as classification, regression, or clustering
• Understand how to evaluate and validate ML models using appropriate metrics and techniques
• Explore methods for hyperparameter tuning to optimize model performance and generalisation
• Gain insights into deploying ML models using Amazon SageMaker for real-time or batch predictions
• Learn best practices for creating scalable, cost-effective, and secure machine learning pipelines in the AWS environment
• Develop the ability to apply ML techniques and AWS services to solve a genuine business problem effectively
• Acquire knowledge of model monitoring and retraining strategies to ensure model performance over time
• Gain proficiency in effectively communicating and presenting ML solutions and insights to stakeholders