Impact of Negative Weights on Performance in Reservoir Computing
Abstract
Reservoir computing provides an efficient framework for time-series prediction because only the readout layer is trained while the recurrent reservoir remains fixed. In this study, we examine how the negative sign ratio of a signed Erdos-Renyi reservoir affects the internal dynamics and forecasting performance of an echo state network on the Mackey-Glass benchmark. To characterize the reservoir responses, we use two Shannon-entropy-based observables, namely node-state entropy and node-frequency entropy, as empirical proxies for the diversity of reservoir states and temporal activation patterns. We find that intermediate negative sign ratios are associated with richer internal dynamics and substantially lower prediction error than the sign-homogeneous extremes for the task considered here. These results suggest that link-sign composition can be a useful structural parameter in reservoir design for chaotic forecasting. The present findings should be interpreted within the scope of the current benchmark and reservoir setting, and broader validation will be required to establish their generality across other tasks, topologies, and controlled spectral conditions.
Related
- Reservoir computing generalized: Exploiting complex dynamics via time-invariant transformation
- Nonlinear pluggable optics: Digital signal processing-free Intensity Modulated Direct Detection links using analog photonic Next Generation Reservoir Computing
- Basin Geometry and Reliable Recall of Dynamical Memories in Reservoir Computing
- Dual-unitary Circuits as a Platform for Quantum Reservoir Computing
- Quantum Reservoir Computing for Attention-like Selective Reproduction
BibTeX
@misc{jeong2026impact,
title = {{Impact of Negative Weights on Performance in Reservoir Computing}},
author = {Yeonsu Jeong and Seonho Nam and Dahan Choi and Mi Jin Lee and Seung-Woo Son},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.06051},
eprint = {2611.06051},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.06051},
}
RIS
TY - UNPB
TI - Impact of Negative Weights on Performance in Reservoir Computing
AU - Yeonsu Jeong
AU - Seonho Nam
AU - Dahan Choi
AU - Mi Jin Lee
AU - Seung-Woo Son
PY - 2026
DA - 2026/11/04
PB - arXiv
DO - 10.48550/arxiv.2611.06051
UR - https://arxiv.org/abs/2611.06051
AB - Reservoir computing provides an efficient framework for time-series prediction because only the readout layer is trained while the recurrent reservoir remains fixed. In this study, we examine how the negative sign ratio of a signed Erdos-Renyi reservoir affects the internal dynamics and forecasting performance of an echo state network on the Mackey-Glass benchmark. To characterize the reservoir responses, we use two Shannon-entropy-based observables, namely node-state entropy and node-frequency entropy, as empirical proxies for the diversity of reservoir states and temporal activation patterns. We find that intermediate negative sign ratios are associated with richer internal dynamics and substantially lower prediction error than the sign-homogeneous extremes for the task considered here. These results suggest that link-sign composition can be a useful structural parameter in reservoir design for chaotic forecasting. The present findings should be interpreted within the scope of the current benchmark and reservoir setting, and broader validation will be required to establish their generality across other tasks, topologies, and controlled spectral conditions.
ER -