Metraipolis › archive › dc_664e4f71c8bd

Impact of Negative Weights on Performance in Reservoir Computing — arXiv:2611.06051

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.06051
License (as archived)
CC0-1.0
Archived
2026-11-05T18:22:38.971Z
SHA-256 of the archived text
7564e1e90eebd8ceca29589b6224c3e06602f1510308f62c7c63cb2be057e30d
Stable URL of this page
https://metraipolis.com/documento/dc_664e4f71c8bd

How to cite

Impact of Negative Weights on Performance in Reservoir Computing — arXiv:2611.06051 — arXiv (en), https://arxiv.org/abs/2611.06051 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_664e4f71c8bd (Metraipolis archive dc_664e4f71c8bd, sha256 7564e1e90eebd8ceca29589b6224c3e06602f1510308f62c7c63cb2be057e30d)
BibTeX
@misc{dc664e4f71c8bd,
  title = {Impact of Negative Weights on Performance in Reservoir Computing — arXiv:2611.06051},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06051},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_664e4f71c8bd; sha256 7564e1e90eebd8ceca29589b6224c3e06602f1510308f62c7c63cb2be057e30d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06051. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Physics and Society (physics.soc-ph) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.06051 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-05T18:15:49.037Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).