Answers are grounded in this paper and cite their sources.
Physical systems exhibiting hysteresis are increasingly being used in neuromorphic and in-memory computing research. Generally, the resistance switching of devices with rate-independent hysteresis are being investigated for their use as trainable weights in neural networks, whereas the dynamics of devices showing rate-dependent hysteresis are being investigate for their potential as nodes, for example in reservoir computing systems. In our work we instead investigate the computing potential of a simple rate-independent hysteresis system. We show that by driving a system of only two linear branches with time-multiplexed inputs it is possible to generate nonlinear transforms and perform timeseries prediction tasks.
No takes yet. Share an insight, caveat, or question.
Jaurigue et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: