Benjamin Scellier

benjamin at rain dot ai

Profile Picture

I am a principal research scientist at Rain.

Before that, I was a resident at Google X, then a resident at Google Zurich, and then a postdoctoral researcher at the Department of Mathematics of ETH Zurich.

I completed my PhD at Mila (University of Montreal) under the supervision of Yoshua Bengio.

Google Scholar


  • Equilibrium propagation is featured in Quanta Magazine
  • New preprint: Agnostic physics-driven deep learning
  • About me

    My main research interests lie at the interface of deep learning, physics and neuroscience. I am more particularly interested in physics-based computation and learning.

    Much of my current research revolves around equilibrium propagation (EP), a novel mathematical framework for gradient-descent-based machine learning. Compared to the more conventional framework based on automatic differentiation (i.e. "backpropagation"), the benefit of the EP framework is that inference and gradient computation are performed using the same physical laws. By suggesting a path to perform the desired computations (inference and learning) more efficiently, this framework may have implications for the design of novel hardware ("accelerators") for deep learning. For more information on EP, Chapter 2 of my PhD thesis provides a (relatively recent) overview. See also these notes on EP.

    Invited Talks

  • March 2023. APS March Meeting. Session on "Learning in physical systems without neurons". "A mathematical framework of learning grounded in physical principles" (invited speaker)
  • May 2021. ICLR 2021. Workshop on energy-based models. "A deep learning theory for neural networks grounded in physics" (invited speaker)
  • August 2020. Neuromorphic Workshop Telluride. "Training nonlinear resistive networks with equilibrium propagation" (invited speaker)