Advanced Deep Learning at Télécom Physique Strasbourg (2026)
This is a course on advanced deep learning taught as a 2nd year option at the engineering school Télécom Physique Strasbourg. It consists of 7*1,75 hours of lectures, and 6*2 hours of tutorials in pytorch.
Here are the lecture slides in pdf [NOTE: the slides will be updated along the progress of the course]:
- cours_IA_avancé_TPS_animated.pdf (Animated)
- cours_IA_avancé_TPS_printable_1-per-page.pdf (1 slide per page)
- cours_IA_avancé_TPS_printable_4-per-page.pdf (4 slides per page)
Here are the materials for the turorial / lab sessions:
- Instructions to setup your environment: Instructions Deep Learning Labs
- Shared folder with tutorials material: Lab Materials
These tutorials were originally created by Paul Magron.
Machine Learning & A.I. at Télécom Physique Strasbourg (2025)
This is an introductory course to AI and machine learning, jointly delivered by Pierre Charbonnier, Hassen Dira and myself to the whole 2nd year class of the engineering school Télécom Physique Strasbourg, between September and December 2025. It consists of 7*1,75 hours of lectures and 7,5 hours of tutorials in scikit-learn. The slides for my lectures are below.
Chapter 1 & 2: Introduction to AI and Machine Learning
Chapter 5: Deep Learning
Chapter 6: Machine Learning in Practice
Autumn School Series in Acoustics (ASSA 2025) in Eindhoven – « Machine Learning for Acoustics »
This is the material for the lecture and tutorial I gave at the 2025 Autumn School Series in Acoustics (ASSA 2025) in Eindhoven, on the topic « Machine Learning for Acoustics » (website), which took place on November 3-7, 2025.
- Lecture: Introduction to Deep Learning (animated and printable slides in pdf)
- Tutorial: Introduction to PyTorch (Jupyter notebook). Corrected notebook.
Summer School 2025 in Strasbourg – « Deep Learning & Applications »
This is the material for the lectures and tutorial I gave at the 2025 summer school on Deep Learning & Applications at the university of Strasbourg (website), which took place on August 25-29, 2025.
- Lecture 1: Introduction to Deep Learning (animated and printable slides in pdf)
- Tutorial: Introduction to PyTorch (Jupyter notebook). Corrected notebook.
- Lecture 3: Unsupervised Learning and Generative Models (animated and printable slides in pdf)
Intelligent Sensing Winter School 2021
On December 9th 2021, I gave a virtual lecture entitled « Machine Learning for Indoor Acoustics » at the Intelligent Sensing Winter School of the Queen Mary University of London. This year’s themes were « AI for sound perception, AI for visual perception, AI for multimodal perception ». You can download the slides here: QMUL_CIS_Winter_School_deleforge_09.12.2021_split.pdf.
IEEE S3P 2019 Summer School in Arenzano
On September 13th 2019, I gave a lecture entitled « Taking the Best of Physics and Machine Learning in Robot Audition » at the IEEE S3P 2019 Summer School in Arenzano, Italy. This year’s theme was « Signal Processing for Autonomous Systems ». You can download the slides here: S3P2019_deleforge_animated.pdf.
Master ISTIC – Module VAI
This a short course taught at the university of Rennes in 2017 and 2018, consisting of 2*2 hours of lectures and 2 hours of tutorial. Here are the slides (In English) of my lectures on Auditory Scene Synthesis and Analysis (Spatialization, Localization, Separation) : cours_ISTIC_casa_2017_english.pdf
Bayesian Learning for Signal Processing
On August the 24th 2015, Mikkel Schmidt and I were invited to give a tutorial on Bayesian Learning for Signal Processing at LVA/ICA 2015’s summer school in Liberec (Czech Republic). Here are the slides of the two parts I presented
- Bayesian Inference (or The adventures of Sir Thomas Bayes!) : bayesian_inference_electronic.pdf
- Bayesian beamforming and multichannel Wiener filtering:
bayesian_multichannel_and_conclusion_electronic.pdf
Unsupervised Learning
This is a series of four 3-hour long practical sessions in Matlab on unsupervised learning taught at the Engineering school Télécom Physique Strasbourg (2021 – 2024).
- Slides of the Lecture
- Exercice 3: Clustering
- Exercice 4: Dimensionality Reduction
- Exercice 5: Dictionary Learning (my_ksvd.m)
