Coordinated by: Federica Granese (Researcher in machine Learning, Inria), and Anaïs Ollagnier (Assistant Professor, Université Côte d’Azur, Inria, CNRS, i3S - 3IA Institute)
FORMAT
Classroom
LOCATION
Campus SophiaTech, Templiers
Prerequisites
- Scientific Bachelor
- Python programming
- Prerequisites and main concepts of machine learning
CAPACITY
24 students
ABOUT THIS MINOR
This minor is also open to students from the SPECTRUM graduate school.
- Summary
-
This foundational course on deep learning introduces the core concepts, techniques, and applications of this rapidly evolving field. It will equip you with the knowledge to understand the potential, challenges, and implications of deep learning and prepare you to contribute to the development of advanced AI technologies.
LEARNING OUTCOMES
- Understand the fundamentals of deep learning.
- Know how to build neural network-based models to process structured data, images, or text.
- Gain proficiency in PyTorch, Keras 3, and JupyterLab.
Throughout the course, you will build and train neural network architectures, including convolutional and recurrent neural networks, and learn to optimize them using strategies like Dropout, BatchNorm, and advanced initialization techniques. By combining theoretical knowledge with hands-on implementation in Python and TensorFlow, you will tackle real-world problems such as object recognition and natural language processing.
Find out more about this minor on Moodle...(course's name "AI : INTRODUCTION TO DEEP LEARNING (DATA ANALYSIS AND DEEP LEARNING)"). - Lecturer
-
- Federica Granese, Researcher in machine Learning, Inria
- Prerequisites
- PYTHON PROGRAMMING
If you do not practice Python on a daily basis,- Autoevaluate yourself to make sure you do have the prerequisites: http://www.i3s.unice.fr/~riveill/python/auto_eval.html
- Review the tutorial: https://www.programiz.com/python-programming/tutorial especially the chapters :
- Python Introduction
- Python Flow Control
- Python Functions
- Python Datatypes
- Python Files
- Train yourself:
- Learn the Basics, Data Science Tutorials, Advanced Tutorials from the tutorial : https://www.learnpython.org/
- Python Data Science Handbook, Jake VanderPlas, 2017, O’REILLY (Part 1 to 4) – free pdf available on internet
- Possible to make lab with Google Colab (no installation needed)
PREREQUISITES AND MAIN CONCEPTS OF MACHINE LEARNING
-
Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, Aurélien Géron, september 2019, O’REILLY
- Bibliography
-
- Statistics and Machine Learning in Python. Edouard Duchesnay, Tommy Löfstedt (presents Python language for machine learning)
- Python Machine Learning. Sebastian Raschka https://github.com/rasbt/python-machine-learning-book-3rd-edition)
- Hands-on machine learning with Scikit-Learn and TensorFlow: concepts, tools, and techniques to build intelligent. A. Géron. O’Reilly (practical)
- Data science : fondamentaux et études de cas: Machine learning avec Python et R. M. Lutz, E. Biernat. Editions Eyrolles (In French, introduction level but requires some maths background: https://elmoukrie.com/wp-content/uploads/2022/05/eric-biernat-michel-lutz-yann-lecun-data-science-_-fondamentaux-et-etudes-de-cas-_-machine-learning-avec-python-et-r-eyrolles-2015.pdf)
- FIDLE: Introduction to Deep Learning: https://fidle.cnrs.fr/w3
- Evaluation
-
- Spring 2026
-
- Test at beginning of the 4th class - 12/03/2026 - 30 min - SophiaTech Templiers room B214 - 25% of the final grade
- Test at beginning of the 8th class - 23/04/2026 - 30 min - SophiaTech Templiers room B214 - 25% of the final grade
- 2 Labs - 50% of the final grade
- Attendance: Attendance is mandatory for the entire range of transversal courses offered by EUR DS4H (minors and projects). A penalty applies for any unjustified absence in minors: 1 point will be deducted from the final grade for each unjustified absence, up to a maximum of 3 points on the final grade of the course unit (UE).
- Fall 2025
-
- Test at beginning of the 4th class - 13/11/2025 - 30 min - SophiaTech Templiers room B215 - 25% of the final grade
- Test at beginning of the 8th class - 11/12/2025 - 30 min - SophiaTech Templiers room B215 - 25% of the final grade
- 2 Labs - 50% of the final grade
- Attendance: Attendance is mandatory for the entire range of transversal courses offered by EUR DS4H (minors and projects). A penalty applies for any unjustified absence in minors: 1 point will be deducted from the final grade for each unjustified absence, up to a maximum of 3 points on the final grade of the course unit (UE).
SCHEDULE
Mind the evaluation modalities and deadlines in the "Evaluation" tab above.
- Spring 2026
-
Date Time Course's title Place 19/02/2026 9h00-10h30 CM : Introduction to Deep Learning Campus SophiaTech, Templiers room B214 10h30-12h30 TD 5/03/2026 8h30-10h30 CM : Neural Networks and Multilayer Perceptrons (MLP) Campus SophiaTech, Templiers room B214 10h30-12h30 TD 12/03/2026 9h00-10h30 CM :Convolutional Neural Networks (CNNs) Campus SophiaTech, Templiers room B214 10h30-12h30 TD 19/03/2026 9h00-10h30 CM : Encoder/Decoder Networks Campus SophiaTech, Templiers room B214 10h30-12h30 TD 26/03/2026 9h00-10h30 CM :Data, Embedding, and Latent Spaces Campus SophiaTech, Templiers room B214 10h30-12h30 TD 2/04/2026 9h00-10h30 CM : Recurrent Neural Networks (RNNs) and Transformers Campus SophiaTech, Templiers room B214 10h30-12h30 TD 9/04/2026 9h00-10h30 CM : Large Language Models (LLMs) Campus SophiaTech, Templiers room B214 10h30-12h30 TD 23/04/2026 9h00-10h30 CM : Learning Optimization (params & metrics) Campus SophiaTech, Templiers room B214 10h30-12h30 TD - Fall 2025
-
Date Time Course's title Place 09/10/2025 9h00-10h30 CM : Introduction to Deep Learning Campus SophiaTech, Templiers room B215 10h30-12h30 TD 16/10/2025 8h30-10h30 CM : Neural Networks and Multilayer Perceptrons (MLP) Campus SophiaTech, Templiers room B215 10h30-12h30 TD 23/10/2025 9h00-10h30 CM :Convolutional Neural Networks (CNNs) Campus SophiaTech, Templiers room B215 10h30-12h30 TD 13/11/2025 9h00-10h30 CM : Encoder/Decoder Networks Campus SophiaTech, Templiers room B215 10h30-12h30 TD 20/11/2025 9h00-10h30 CM :Data, Embedding, and Latent Spaces Campus SophiaTech, Templiers room B215 10h30-12h30 TD 27/11/2025 9h00-10h30 CM : Recurrent Neural Networks (RNNs) and Transformers Campus SophiaTech, Templiers room B215 10h30-12h30 TD 04/12/2025 9h00-10h30 CM : Large Language Models (LLMs) Campus SophiaTech, Templiers room B215 10h30-12h30 TD 11/12/2025 9h00-10h30 CM : Learning Optimization (params & metrics) Campus SophiaTech, Templiers room B215