#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