Nanoelectronic implementation of Equilibrium Propagation

Marie Drouhin; Clément Turck; Kamel-Eddine Harabi; Adrien Renaudineau; Thomas Bersani-Veroni; Elisa Vianello; Jean-Michel Portal; Julie Grollier; Damien Querlioz

doi:10.1117/12.2677568

28 September 2023 Nanoelectronic implementation of Equilibrium Propagation

Marie Drouhin, Clément Turck, Kamel-Eddine Harabi, Adrien Renaudineau, Thomas Bersani-Veroni, Elisa Vianello, Jean-Michel Portal, Julie Grollier, Damien Querlioz

Author Affiliations +

Proceedings Volume PC12655, Emerging Topics in Artificial Intelligence (ETAI) 2023; PC1265507 (2023) https://doi.org/10.1117/12.2677568
Event: SPIE Nanoscience + Engineering, 2023, San Diego, California, United States

Abstract

As deep learning continues to grow, developing adapted energy-efficient hardware becomes crucial. Learning on a chip requires hardware-compatible learning algorithms and their realization with physically imperfect devices. Equilibrium Propagation is a training technique introduced in 2017 by Yoshua Bengio which gives gradient estimates based on a spatially local learning rule, making it both more biologically plausible and more hardware compatible than backpropagation. This work uses the Equilibrium Propagation algorithm to train a neural network with hardware-in-the-loop simulations using hafnium oxide memristor synapses. Realizing this type of learning with imperfect and noisy devices paves the way for on-chip learning at very low energy.

Conference Presentation

Citation Download Citation

Marie Drouhin, Clément Turck, Kamel-Eddine Harabi, Adrien Renaudineau, Thomas Bersani-Veroni, Elisa Vianello, Jean-Michel Portal, Julie Grollier, and Damien Querlioz "Nanoelectronic implementation of Equilibrium Propagation", Proc. SPIE PC12655, Emerging Topics in Artificial Intelligence (ETAI) 2023, PC1265507 (28 September 2023); https://doi.org/10.1117/12.2677568

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available