I am a Full Professor at Université Côte d'Azur. Since September 2019, I joined i3S lab (UMR 7271 CNRS / UNS) and Polytech Nice Sophia school. I am a member of the Modelisation, Simulation & Neurocognition group of SPARKS team.
Before joining Universté Côte d'Azur, I was an Associate Professor at Université de Lille from 2007 to 2019, with the Computer Science department of l'IUT 'A', and CRIStAL lab (UMR 9189 CNRS / Univ. Lille).
My main research interest is in the use of Spiking Neural Networks for Machine Learning, Computer Vision and Pattern Recognition. I belive that the so-call third generation of neural network models, strongly inspired from biology and neurosciences, is a good candidate for a paradigm change in machin learning with respect to data-hungry and power-hungry popular methods. Spiking networks show many interesting features for this paradigm change, such as their unsupervised training with Spike-Timing-Dependant Plasticity rules, and their implementation on ultra-low-power neuromorphic hardware. And yet, a number of challenges lie ahead before they become a realistic alternative for facing the ever-growing demand in machine learning.
I am the coordinator of the CHIST-ERA european programme APROVIS3D (1/4/2020-31/3/2023), grant number ANR-19-CHR3-0008-03.
I participate in the ANR-funded project DeepSee (project lead: Pr. Benoît Miramond, LEAT), grant number ANR-20-CE23-0004-04.
Regarding teaching, I am involved in several classes in Polytech Nice Sophia in 3rd and 4th years, and also in the Mater of Mathematical Engineering, in Mod4NeuCog, and in the CS department of IUT.
I am the coordinator of the Data Science track of the EIT Digital Master School at University Côte d'Azur from Sept. 2020 (the Head of our EIT hub is my colleague Pr. Françoise Baude).
1. Call PhD candidate from Oct. 2021(application deadline: May 1st 2021, interviews from May 3rd): Neuromorphic Stereo Vision with Event Cameras
- Stereopsis enables depth perception of the world, which is a key feature for both artificial and human visual processing systems. Besides, depth is an essential requirement for many practical applications, ranging from fine object manipulation in robotics, to autonomous driving for vehicles. In this PhD proposa, we wish to design and implement a neuromorphic model for stereo matching using event cameras. The project will extend a previous internship work done in the lab in 2020.
2. Call for PhD candidate from Oct. 2021 (application deadline: May 1st 2021, interviews from May 3rd): Neuromorphic Visual Odometry for Intelligent Vehicles with a Bio-inspired Vision Sensor (also with AID)
- This thesis aims at exploiting biologically devised ‘short cuts’ used by insects with small brains and relatively simple nervous systems to see and perceive their world in real-time. The objective is to develop a biologically-inspired omni-directional event camera model to perform real-time ego-motion estimation and environment mapping. In collaboration with Dr. Andrew Comport.
3. Call for PhD candidate for CSC grant from Oct. 2021 (application deadline is passed): Towards Spike-Based Machine Learning
- Spiking Neural Networks show many interesting features for a necessary paradigm in information processing and machine learning --in order to face the ever-growing demand in large scale computation--, such as their unsupervised training with Spike-Timing-Dependant Plasticity rules, and their implementation on ultra-low-power neuromorphic hardware. And yet, a number of challenges lie ahead before they become a realistic alternative to deep CNN. The objective this PhD proposal is to gain an in-depth understanding of the theoretical computational properties of SNNs that will help to exhibit their fundamental limits.
Topic presentation slides for Call 2018 Analog Computing for Artificial Intelligence (ACAI), during CHIST-ERA Projects Seminar 2021
Laboratoire d'Informatique, Signaux et Systèmes de Sophia-Antipolis (I3S) - UMR7271 - UNS CNRS
2000, route des Lucioles - Les Algorithmes - bât. Euclide B 06900 Sophia Antipolis - France