Professional Training · Applied AI Engineering Track
Practical Data Science with Amazon SageMaker
A one-day, practical course that follows a single real-world use case through the whole data science process in Amazon SageMaker. You will explore and visualise the dataset, prepare it and engineer features, train models with built-in algorithms, review and tune performance through hyperparameter optimisation, run batch and real-time predictions, and analyse the cost of errors to set a sensible model threshold.
Authorised Instructors
Eric Tai
Head, Technology
- Machine Learning Engineer – Associate
- Security – Specialty
- DevOps Engineer – Professional
- Solutions Architect – Professional
- +4 more
Hui Liang
Chief Digital Officer
- Machine Learning Engineer – Associate
- Security – Specialty
- Generative AI Developer – Professional
- Solutions Architect – Professional
- +5 more
Any of these AWS Authorised Instructors may deliver this class, depending on the scheduled run. Trainers confirmed on enrolment.
Who Should Attend
- Data Scientists: Practitioners taking a use case from data to deployed model.
- Machine Learning Practitioners: Staff applying ML techniques to business problems.
- Developers: Developers building data-driven applications on AWS.
- Systems Architects: Architects designing environments for data science work.
Prerequisites
This is an intermediate course. To get the most from it, you should have:
Experience with the Python programming language.
Familiarity with fundamental machine learning algorithms.
Familiarity with the NumPy and pandas libraries is helpful.
Some familiarity with putting machine learning models into production.
Learning Objectives
In this course, you will learn to:
Explore the dataset: Visualise the data and understand how its attributes relate.
Prepare data for training: Clean the dataset and engineer features for modelling.
Train with built-in algorithms: Build models in Amazon SageMaker using the supplied algorithms.
Tune performance: Apply hyperparameter optimisation to find better model parameters.
Deploy and serve: Run batch predictions and configure endpoints for real-time inference at scale.
Evaluate in business terms: Use A/B testing and cost-of-error analysis to set the model threshold.
Certification
A MY Code Campus certificate of completion is awarded for Practical Data Science with Amazon SageMaker.
In-person in Kuala Lumpur or live virtual. Team & enterprise rates available.