Minor Artificial Intelligence: Introduction to Deep Learning

Coordinated by: 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

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. 
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. 
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
  • Anaïs Ollagnier, Assistant Professor, Université Côte d’Azur, Inria, CNRS, i3S
Prerequisites
PYTHON PROGRAMMING

If you do not practice Python on a daily basis,
PREREQUISITES AND MAIN CONCEPTS OF MACHINE LEARNING
Bibliography
Evaluation
  • Test at beginning of the 4th class -  06/11/2025 - 30 min - SophiaTech Templiers room B215 - 25% of the final grade
  • Test at beginning of the 8th class - 04/12/2025 - 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 Fall 2025

 
Mind the evaluation modalities and deadlines in the "Evaluation" tab above.
 
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
10h30-12h30 TD