Dynamical Diversity for Reservoir Computing in Reconfigurable Nanomechanics

2026-09-24

AI Summary

This study addresses the limited information representation capacity of single-mode nanoelectromechanical (NEMS) resonators in physical reservoir computing by proposing a dynamic diversity strategy based on dual-mode NEMS resonators. Through complementary modal excitation, the method achieves single-port multimodal response multiplexing and feature concatenation, while leveraging Duffing nonlinear dynamics to expand the high-dimensional feature space. This approach enhances nonlinear temporal processing capabilities without requiring additional hardware. Experimental results demonstrate that the proposed method reduces the test error on the NARMA-2 task by over 28-fold compared to single-mode counterparts and significantly outperforms electrical feedthrough baselines. These findings validate the effectiveness of multimodal multiplexing in improving reservoir computing performance.

Abstract

Physical reservoir computing uses nonlinear dynamics and a trained linear readout to process information. Nanoelectromechanical (NEMS) resonators combine geometric Duffing nonlinearity with fading memory, but most electromechanical implementations use a single resonance mode. Here, we demonstrate reservoir computing with two interacting modes of a single NEMS resonator measured through one readout port. We introduce dynamical diversity through complementary modal drive settings: the same input sequence is replayed under different allocations of drive amplitude between the modes, and the responses are concatenated into a single feature matrix. This multiplexing expands the representation available to the readout without additional devices or training of internal parameters. On NARMA-2, it reduces variance-normalized test error more than 28-fold relative to single-mode operation and more than threefold relative to the best individual two-mode setting. Linear memory-capacity measurements show that accessible recall spans only a few symbols at the tested symbol duration. Its rapid decline with delay, consistent with mechanical dissipation, accompanies rising NARMA error and the eventual loss of multiplexing gains at higher orders. We also use electrical feedthrough as an internal reference for assessing the computational contribution of the NEMS response. Separate linear readouts are trained on feedthrough features and features derived from the measured NEMS response, using the same recordings and matched drive settings and processing. On challenging nonlinear mapping tasks, the multiplexed NEMS features yield substantially lower errors than the feedthrough features. These results demonstrate how dynamical diversity through variations in modal drive amplitudes expands the computational capability of a single multimode NEMS resonator.

Problem

• Reservoir Computing
• NEMS Resonators
• Dynamical Diversity
• Multimode Interaction
• Fading Memory

Innovation

• Reservoir Computing
• NEMS Resonators
• Dynamical Diversity
• Modal Multiplexing
• Nonlinear Dynamics