Seules les adresses mails institutionnelles sont acceptées lors de la création d'un compte. La création de compte est modérée, merci d'attendre leur validation.
Only institutional email addresses will be accepted when asking for an account. Account creation is moderated, please wait until then.
Séminaires LLR

Des synapses électroniques capables d’apprendre : vers un cerveau artificiel ?

by Julie Grollier (CNRS Thalès)

lundi 12 juin 2017 de à (Europe/Paris)
at LLR ( Seminar room )
Description
In the last five years, Artificial Intelligence has made striking progress, and now defeating humans at subtle strategy games, such as Go, and even Poker. However, these algorithms are running on traditional processors which have a radically different architecture than the biological neural networks they are inspired from. This considerably slows them down and requires massive amounts of electrical power, more than ten thousand times what the brain typically need to function. This energy dissipation is not only becoming an environmental issue, but it also sets a limit to the size of neural networks that can be simulated. We are at a point where we need to rethink the way we compute, and build hardware chips directly inspired from the architecture of the brain. This is a challenge. Indeed, contrarily to current electronic systems, the brain is a huge parallel network closely entangling memory and processing. 

In this talk, I will show that, for building the neuromorphic chips of the future, we will need to emulate functionalities of synapses and neurons at the nanoscale. I will review the recent developments of memristive nano-synapses and oscillating nano-neurons, the physical mechanisms at stake, and the challenges in terms of materials. Finally, I will present the first achievements of neuromorphic computing with novel nanodevices and the fascinating perspectives of this emerging field.