Score: 0

Learning Dynamics in Memristor-Based Equilibrium Propagation

Published: December 13, 2025 | arXiv ID: 2512.12428v1

By: Michael Döll, Andreas Müller, Bernd Ulmann

Potential Business Impact:

Makes computers learn faster and use less power.

Business Areas:
Semiconductor Hardware, Science and Engineering

Memristor-based in-memory computing has emerged as a promising paradigm to overcome the constraints of the von Neumann bottleneck and the memory wall by enabling fully parallelisable and energy-efficient vector-matrix multiplications. We investigate the effect of nonlinear, memristor-driven weight updates on the convergence behaviour of neural networks trained with equilibrium propagation (EqProp). Six memristor models were characterised by their voltage-current hysteresis and integrated into the EBANA framework for evaluation on two benchmark classification tasks. EqProp can achieve robust convergence under nonlinear weight updates, provided that memristors exhibit a sufficiently wide resistance range of at least an order of magnitude.

Page Count
22 pages

Category
Computer Science:
Machine Learning (CS)