Deep learning
This page gathers material for the Deep Learning course at EDHEC (Spring semester, 2026). Instructor for this course is Romain Tavenard, professor atUseful links: In this course, we will use
keras v3 and pytorch.
Execute the following commands to install these libraries (no need for that on Google Colab since these libraries are pre-installed there):
pip install scikit-learn pillow matplotlib pip install --upgrade torch pip install --upgrade keras
1. An introduction to deep learning
Course details and a first model: the Perceptron.2. Multi Layer Perceptrons
Stacking perceptrons in layers for better expressivity.3. Optimization
- Slides (pdf)
- Losses (lecture notes)
- Optimization (lecture notes)
- Regularization (lecture notes)
-
Multi-Layer Perceptron (lab)
-
Multi-Layer Perceptron (lab, with solution)
4. Images and Convolutional models
An overview of 2d convolutional neural networks.- Slides (pdf)
- Convolutional Neural Networks (lecture notes)
-
Images and ConvNets (lab)
-
Images and ConvNets (lab, with solution)
5. Time series and Sequences
Models for sequential data.- Slides (pdf)
- Convolutional Neural Networks (lecture notes)
- Recurrent Neural Networks (lecture notes)
-
Sequences (lab)
-
Sequences (lab, with solution)