fr
en
Putting data science into practice with Amazon SageMaker
Your AI use cases need appropriate services and evaluated outcomes. With AWS, connect data, models and integration to assess the technical options more clearly. Develop a framework for designing experiments and assessing implementation requirements.
- Duration
- 1 day 7 hours
- Code
- AWS12FR Code
Presentation
AWS offers a comprehensive ecosystem of AI and machine learning (ML) services. This includes Amazon SageMaker for developing, training and deploying models, alongside tools such as Amazon CodeWhisperer for coding assistance. These tools enable businesses to harness ML to solve business problems and improve productivity.
This intensive course provides practical skills to master the use of data science and related AWS services, particularly Amazon SageMaker. You will explore the machine learning lifecycle in depth, from data preparation and evaluation to model deployment. You will also address responsible ML considerations and operational challenges. Through demonstrations and hands-on labs, you will learn to prepare, train, evaluate and deploy ML models.
By the end of this one-day programme, you will have developed the expertise to understand and apply data science fundamentals responsibly and effectively on AWS. You will master key concepts, best practices and essential tools to unlock the full potential of predictive modelling in your organisation.
As a premium training partner (ATP) authorised by Amazon Web Services, Oo2 offers skills-based and certification training that meets the organisation's rigorous quality standards.
Objectives
By the end of this Amazon SageMaker course, you will be able to:
- Identify relevant applications of different types of machine learning to address business needs;
- describe key roles and stages in the team-based development and deployment of AI systems;
- explain how AWS tools, particularly Amazon SageMaker, help solve common business problems through data science;
- master data preparation and analysis techniques for predictive modelling;
- train ML models using Amazon SageMaker;
- apply predictive model evaluation and optimisation methods, including hyperparameter tuning;
- deploy a machine learning solution to an endpoint to generate real-time predictions;
- understand the operational challenges of putting AI models into production and maintaining them;
- map AWS services to specific functions in the machine learning value chain.
Program
Module 1: Introducing machine learning
- The benefits of machine learning (ML) for solving business problems.
- Different types of machine learning approaches.
- Framing a business problem for ML.
- Prediction quality in ML.
- Processes, roles and responsibilities for ML projects.
Module 2: Preparing a dataset
- Data analysis and preparation.
- Data preparation tools.
- Reviewing Amazon SageMaker Studio and notebooks (demo).
Lab:
- Prepare data with SageMaker Data Wrangler.
Module 3: Training a model
- The steps involved in training a model.
- Selecting an algorithm.
- Training the model in Amazon SageMaker.
- Using Amazon CodeWhisperer in SageMaker Studio Notebooks (demo).
Lab:
- Train a model with Amazon SageMaker.
Module 4: Evaluating and tuning a model
- Model evaluation.
- Model tuning and hyperparameter optimisation.
Lab:
- Tune models and optimise hyperparameters with Amazon SageMaker.
Module 5: Deploying a model
- Implementing model deployment.
Lab:
- Deploy a model to a real-time endpoint and generate a prediction.
Module 6: Understanding operational challenges
- Responsible ML.
- The ML team and MLOps.
- Automation.
- Monitoring.
- Updating models (model testing and deployment).
Module 7: Exploring other model-building tools
- Different tools for different skill levels and business needs.
- No-code ML with Amazon SageMaker Canvas.
- Using Amazon SageMaker Studio Lab (demo).
Lab (optional):
- Integrate a web application with an Amazon SageMaker model endpoint.
Audience
This course is intended for:
- DevOps engineers who want to collaborate effectively with data scientists and integrate applications with machine learning;
- Application developers who want to build applications incorporating ML.
Prerequisites
The following prerequisites are recommended for this AWS course:
- Familiarity with core AWS services: completion of the AWS Technical Essentials course or equivalent knowledge of core Amazon Web Services concepts and services is recommended.
- Basic Python programming skills: elementary knowledge of Python is required, as examples and hands-on exercises use this language.
- Basic statistics knowledge: understanding fundamental statistical concepts will help you grasp machine learning principles and model evaluation.
Teaching and assessment methods
- Initial skills assessment
- Training materials provided to participants
- Continuous assessment throughout the course
- End-of-course feedback questionnaire
- Combination of theory and practical application
- Attendance records
- Post-course follow-up evaluation
- Practical exercises
Course highlights
- AWS-certified expert trainers: learn from recognised, AWS-certified trainers with in-depth knowledge of data science and machine learning practices, as well as AWS tools and services such as Amazon SageMaker.
- Interactive hands-on learning: master data science tools and techniques on AWS through concrete demonstrations and practical labs. Prepare to address real-world challenges in data preparation and ML model training, evaluation and deployment in the cloud.
- Key skills development: carefully designed content helps you acquire essential skills in designing and implementing machine learning solutions, automating predictive modelling processes and efficiently managing AWS infrastructure for data science.
Dates and sessions
Choose the date and delivery format that suit you.
No upcoming sessions are currently available.
AWS, Amazon SageMaker, Amazon CodeWhisperer and other AWS marks are registered trademarks of Amazon.com, Inc. or its affiliates.