Chaire Artificial Vision

#apprentissages avec peu de données ou des données complexes
#langage #Neuroscience et IA #Robotique et IA

Artificial vision has often been described as one of the key remaining challenges to be solved before machines can act intelligently. Recent developments in a branch of machine learning known as deep learning have catalyzed impressive gains in machine vision.

Yet, modern deep learning algorithms remain outmatched by the power and versatility of the brain. Our long-term goal is thus to understand the neural computations supporting human perception towards the development of a new breed of neuroscience-inspired AI algorithms.

There is little doubt that even a partial solution to the question of which computations are carried out by the visual cortex would be a major breakthrough: It would begin to explain one of our most amazing abilities, vision; and it would open doors to other aspects of intelligence such as language, planning or reasoning.

It would also help connect neurobiology and mathematics, making it possible to develop computer algorithms that follow the information processing principles used by biological organisms and honed by natural evolution.

IA acceptable, certifiable & collaborative

Porteur :
Thomas Serre, Brown University and ANR-3IA ANITI

Équipe
Amor Ben Tanfous (Postdoctoral Research Associate)
Victor Boutin (Postdoctoral Research Associate)
Mohit Vaishnav (PhD)
Aimen Zerroug (PhD)
Mathieu Chalvidal (PhD)

Sites
https://vivo.brown.edu/display/tserre

Publications
https://serre-lab.clps.brown.edu/publications/

The Team

Thomas Serre (porteur de chaire)
Dr. Serre holds an International Chair in AI within ANITI. He is also an Associate Professor in the Cognitive Linguistic & Psychological Sciences Department at Brown University in Providence, RI (USA). He received a
Ph.D. in Neuroscience from MIT in 2006 and an MSc in EECS from Télécom Bretagne (France) in 2000. His research seeks to understand the neural computations supporting visual perception and has been
featured in the BBC series “Visions from the Future” and other news articles (The Economist, New Scientist, Scientific American, IEEE Computing in Science and Technology, Technology Review, and Slashdot). Dr. Serre is Faculty Director of the Center for Computation and Visualization and Associate Director of the Center for Computational Brain Science at Brown University. Dr. Serre has served as an area chair and a senior program committee member for top-tier machine learning and computer vision
conferences including AAAI, CVPR, ICLR, and NeurIPS. He was the recipient of an NSF Early Career Award as well as DARPA’s Young Faculty Award and Director’s Award.

Victor Boutin (Postdoctoral Research Associate)
Victor Boutin is a Postdoctoral Research Associate at the Artificial and Natural Intelligence Toulouse Institute (ANITI). He received a Ph.D in computational neuroscience and artificial intelligence from Aix-Marseille University (France) in 2020 and a MSc in Statistics and Applied Mathematics from Ecole Centrale (France) in 2011. His research seeks to understand how the visual cortex can learn useful representations to generalize visual concepts from a small amount of labeled datas.

Mohit Vaishnav (PhD)
Mohit Vaishnav is a Ph.D. student at the Artificial and Neural Intelligence Toulouse Institute (ANITI). He obtained his Master’s Degree in Computer Vision and Robotics from the Erasmus Joint Masters program known as VIBOT, from the University of Bourgogne (France), University of Girona (Spain) and Heriot-Watt University (UK) in 2019. His research interests include topics related to Computer Vision and Neural
Networks. He is currently working on modeling attention mechanisms to help solving visual reasoning
tasks.

Amor Ben Tanfous (Postdoctoral Research Associate)
Amor Ben Tanfous is a postdoctoral research associate at the Artificial and Neural Intelligence Toulouse Institute (ANITI). He received a Ph.D. in Computer science from University of Lille in 2019, a MSc double-degree from National Engineering School of Tunis and Paris Descartes University (France) in 2016, and an engineering degree from National Institute of Applied Sciences and Technology (Tunisia) in 2016. He is currently interested in solving computer vision problems in the interface of machine learning and behavior analysis.

Aimen Zerroug (PhD)
Aimen Zerroug is a graduate student at ANITI. He joined the program after obtaining a multidisciplinary engineering degree from CentraleSupelec in 2019 with a major in computer science. His research
interests are at the intersection of neuroscience and deep learning and he’s currently working on eveloping deep learning architectures inspired from neural circuits in the brain.

Mathieu Chalvidal (PhD)
Mathieu Chalvidal is a Ph.D. candidate at ANITI since January 2020. He studied at Centrale Supelec University (France) where he obtained a Master’s degree in Applied Mathematics and a Master in Artificial Intelligence in 2019. He also holds a Master’s degree in Management at ESSEC Business school where he specialized in Statistics. His research interests include dynamical systems, information theory, self-supervised and variational learning and their relationship with bio-inspired attentional models.