activity
20242026
collaborators

5 papers

cond-mat.mes-hall2026

Neuromorphic computing with optomechanical oscillators

Andrea Gaspari, Rémi Avriller, Florian Marquardt +1

The increasing resource demands of artificial neural networks have prompted the exploration of novel platforms better suited for machine learning. In this context, phase oscillator…

cs.LG2026

Dependence of Equilibrium Propagation Training Success on Network Architecture

Qingshan Wang, Clara C. Wanjura, Florian Marquardt

The rapid rise of artificial intelligence has led to an unsustainable growth in energy consumption. This has motivated progress in neuromorphic computing and physics-based training…

physics.optics2025

Training nonlinear optical neural networks with Scattering Backpropagation

Nicola Dal Cin, Florian Marquardt, Clara C. Wanjura

As deep learning applications continue to deploy increasingly large artificial neural networks, the associated high energy demands are creating a need for alternative neuromorphic…

quant-ph2024

Quantum Equilibrium Propagation for efficient training of quantum systems based on Onsager reciprocity

Clara C. Wanjura, Florian Marquardt

The widespread adoption of machine learning and artificial intelligence in all branches of science and technology has created a need for energy-efficient, alternative hardware plat…

physics.app-ph2024

Training of Physical Neural Networks

Ali Momeni, Babak Rahmani, Benjamin Scellier +25

Physical neural networks (PNNs) are a class of neural-like networks that leverage the properties of physical systems to perform computation. While PNNs are so far a niche research…