Administrative Information
| Title | Data architecture |
| Duration | 60 |
| Module | B |
| Lesson Type | Interactive Session |
| Focus | Practical - Organisational AI |
| Topic | Data architecture |
Keywords
Data Architecture,Machine Learning pipeline,MLOps,
Learning Goals
- To know the basic data architectures in Machine Learning
- Pose questions about the most suited data architectures
Expected Preparation
Learning Events to be Completed Before
Obligatory for Students
- Data Analysis Process
- Machine Learning Models
- DevOps
- CI/CD
Optional for Students
None.
References and background for students
- DevOps
- CI/CD
Recommended for Teachers
Lesson materials
Instructions for Teachers
Use the following outline:
- Introduction to the discussion
- What are the most diffused architectures for ML Systems?
- What is a typical ML pipeline?
- What is the MLOps?
- How it is possible to automate and orchestrate a ML pipeline?
- How it is possible configure a Continuous Integration/ Continuous Delivery CI/CD system for the ML pipeline using the Cloud?
- Questions and further discussion on topics suggested by students
- Discussion
- What are the characteristics of the Tensor Flow eXTended (TFX) architecture?
- How can Cloud support the TFX model?
- How How it is possible to automate and orchestrate the TFX pipeline?
- How it is possible configure a Continuous Integration/ Continuous Delivery CI/CD system for the TFX pipeline?
- Questions and further discussion on topics suggested by students
- Conclusions
- Summing up and discussing the lesson outcomes:
- Main features of an ML System Architecture and of ML pipelines
- MLOPs
- Automating and orchestrating a ML pipeline with reference to the TFX model
- Conclusive remarks
- Summing up and discussing the lesson outcomes:
Time schedule
| Duration (min) | Description | Concepts |
|---|---|---|
| 20 | Introduction to the discussion | ML System Architecture, ML Pipeline |
| 30 | Discussion | ML in production examples |
| 10 | Summing up and conclusive remarks |
Acknowledgements
The Human-Centered AI Masters programme was Co-Financed by the Connecting Europe Facility of the European Union Under Grant №CEF-TC-2020-1 Digital Skills 2020-EU-IA-0068.