Accelerating Inference and Training at the Edge

Join us for a talk by Maxence Ernoult, Research Scientist at Rain, on accelerating inference and training at the edge.

Maxence will present us Rain’s vision and technological roadmap to build hardware optimized for inference and training at the edge including both the hardware and algorithm aspects with an emphasis on why physical and mathematical principles matter more to him than biological inspiration.

Social share preview for Accelerating Inference and Training at the Edge

Upcoming Workshops

Open-Source Neuromorphic Research Infrastructure: A Community Panel
Jens E. Pedersen, Hananel Hazan, James Knight, Alexandre Marcireau, Gregor Lenz, Dylan Muir, Christian Pehle, Terry Stewart, Marcel Stimberg
July 30, 2025
17:00 - 18:30 CEST

About the Speaker

Maxence Ernoult graduated from Ecole Polytechnique and the University of Cambridge in 2016, specializing in applied mathematics and theoretical physics. His PhD research was conducted in neuromorphic computing at Sorbonne University, in collaboration with Mila. During this time, he specialized in developing hardware-friendly alternatives to backpropagation and played a significant role in scaling up several of these alternatives, including Equilibrium Propagation and Difference Target Propagation. This work was undertaken alongside notable figures such as Ben Scellier, Blake Richards, and Yoshua Bengio. In 2021, Maxence joined IBM Research, focusing on AI safety. Subsequently, in 2022, he began a new position at Rain.

Inspired? Share your work.

Share your expertise with the community by speaking at a workshop, student talk, or hacking hour. It’s a great way to get feedback and help others learn.

Related Workshops

Project Phasor - Kickoff

Project Phasor - Kickoff

Brian Anderson and others discuss the newly launched Project Phasor, aiming to organize efforts towards neuromorphic and NeuroAI virtualization and compilation.

Spyx Hackathon: Speeding up Neuromorphic Computing

Spyx Hackathon: Speeding up Neuromorphic Computing

Explore the power of Spyx in a hands-on hackathon session and dive into the world of neuromorphic frameworks with Kade Heckel.

PEPITA - A Forward-Forward Alternative to Backpropagation

PEPITA - A Forward-Forward Alternative to Backpropagation

Explore PEPITA, a forward-forward approach as an alternative to backpropagation, presented by Giorgia Dellaferrera. Learn about its advantages and implementation with PyTorch.