SeminarPast EventArtificial Intelligence

Dynamical Neuromorphic Systems

Schedule
Monday, June 14, 2021
22:00 UTC
Julie Grollier

Dr.

CNRS/Thales lab, Palaiseau, France

Host: IEEE Brain

Event Information

Host

IEEE Brain

Duration

70 minutes

Abstract

In this talk, I aim to show that the dynamical properties of emerging nanodevices can accelerate the development of smart, and environmentally friendly chips that inherently learn through their physics. The goal of neuromorphic computing is to draw inspiration from the architecture of the brain to build low-power circuits for artificial intelligence. I will first give a brief overview of the state of the art of neuromorphic computing, highlighting the opportunities offered by emerging nanodevices in this field, and the associated challenges. I will then show that the intrinsic dynamical properties of these nanodevices can be exploited at the device and algorithmic level to assemble systems that infer and learn though their physics. I will illustrate these possibilities with examples from our work on spintronic neural networks that communicate and compute through their microwave oscillations, and on an algorithm called Equilibrium Propagation that minimizes both the error and energy of a dynamical system.

We use essential cookies to run the site. Analytics cookies are optional and help us improve World Wide. Learn more.