PROTOTYPE PROGRAMME: Machine Learning for Defence
IMPORTANT: This prototyped programme is EXCLUSIVE FOR partners of the ASSETs+ consortium and associated stakeholders. If you want to join the ASSETs+ Stakeholders Group and become part of our ecosystem, please, click here.
GENERAL INFORMATION
Format: On-site
Language: French / English
EQF level: 6
Hours: 56
Instructors:
PESQUET Baptiste, Bordeaux INP
AIRIMITOAIE Tudor-Bogdan, UBx
ZEMMARI Akka, UBx
Hosting Department:
Unité de formation – Science de l’Ingénieur
(Training Unit – Engineering Science)
Access conditions:
B2 English level
Mathematics and Computer Science: linear algebra, statistics, programming
Python programming
Problem specification and solving
Python
Host institution: University of Bordeaux (France)
PROGRAMME CALENDAR
| MODULE 1 (January, 2022) | ||
| 26/01 | 8.30 – 10.15 | Introduction to Machine Learning |
| 10.30 – 12.00 | Conference with a professional of the sector | |
| 14.00 – 17.30 | Launch of the mini-projects in groups | |
| 27/01 | 8.30 – 10.15 | Machine Learning Fundamentals |
| 10.30 – 12.00 | ||
| 14.00 – 17.30 | Mini-projects in groups | |
| 28/01 | 8.30 – 10.15 | K-NN and linear models |
| 10.30 – 12.00 | ||
| 14.00 – 17.30 | Mini-projects in groups | |
| MODULE 2 (February, 2022) | ||
| 14/02 | 8.30 – 10.15 | Bayes and SVM |
| 10.30 – 12.00 | Conference with a professional of the sector | |
| 14.00 – 17.30 | Mini-projects in groups | |
| 15/02 | 8.30 – 10.15 | ANN and CNN (Neural Networks) |
| 10.30 – 12.00 | ||
| 14.00 – 17.30 | Mini-projects in groups | |
| MODULE 3 (March, 2022) | ||
| 16/03 | 8.30 – 10.15 | Unsupervised Learning |
| 10.30 – 12.00 | Conference with a professional of the sector | |
| 14.00 – 17.30 | Mini-projects in groups | |
| 17/03 | 8.30 – 10.15 | ML issues and ML Ops |
| 10.30 – 12.00 | ||
| 14.00 – 17.30 | Mini-projects in groups | |
| 18/03 | 8.30 – 10.15 | Presentation of the mini-projects |
| 10.30 – 12.00 | ||
| 14.00 – 17.30 | Closing session | |
LEARNING OUTCOMES
Learning outcomes that will be implemented:
– Machine Learning overview
– Model training & evaluation
– Core Machine Learning algorithms
– Machine Learning issues & MLOps
– Prepare datasets for training
– Build Machine Learning models on various data types
– Use standard Python libraries for Machine Learning
– Understand the benefits and limits of Machine Learning approaches
– Apply Machine Learning wisely, in accordance with ethical rules
Knowledges:
• algorithms
• decision support systems
• mathematical modelling in missions
• model based system engineering
• principles of artificial intelligence
• signal processing
• computer programming (python, c, c++, r, java, matlab, lisp, prolog)
• data mining
Skills:
• analyse big data
• apply deep learning architectures
• demonstrate willingness to learn
• run simulations
• using digital tools for processing sound and images
• utilise machine learning
• solving problems
• address problems critically
• develop data processing applications
• develop software prototype
• identify service requirements
• interact through digital technologies
• use ict systems
• use interface description language
• use online communication tools
• use specific data analysis software
TARGETED JOB PROFILES
- Data scientist
- Data analyst
- ICT Intelligence Systems designer
