Metraipolis › archive › dc_0bd36cd08476

Empirical Boundaries of Reservoir Computing for Few-Shot Sequence Pattern Tasks — arXiv:2610.19997

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.19997
License (as archived)
CC0-1.0
Archived
2026-10-15T14:19:15.781Z
SHA-256 of the archived text
988aeba102ca65bb04bd2ac2eecf86d4224135a32439e6afaeaa1cb37c8feba6
Stable URL of this page
https://metraipolis.com/documento/dc_0bd36cd08476

How to cite

Empirical Boundaries of Reservoir Computing for Few-Shot Sequence Pattern Tasks — arXiv:2610.19997 — arXiv (en), https://arxiv.org/abs/2610.19997 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0bd36cd08476 (Metraipolis archive dc_0bd36cd08476, sha256 988aeba102ca65bb04bd2ac2eecf86d4224135a32439e6afaeaa1cb37c8feba6)
BibTeX
@misc{dc0bd36cd08476,
  title = {Empirical Boundaries of Reservoir Computing for Few-Shot Sequence Pattern Tasks — arXiv:2610.19997},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19997},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0bd36cd08476; sha256 988aeba102ca65bb04bd2ac2eecf86d4224135a32439e6afaeaa1cb37c8feba6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19997. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Efficient sequence modeling remains a fundamental challenge in machine learning. Despite the success of Transformers, recurrent neural networks (RNNs) have recently re-emerged as efficient alternatives. Particularly, Echo State Networks (ESNs) offer a compelling framework of randomized RNNs that have been extensively studied for time-series forecasting and dynamical systems. This paper presents an empirical analysis of distributional, architectural, and optimization variants of ESNs evaluated on few-shot sequence-to-sequence (seq2seq) pattern tasks. These synthetic tasks utilize discrete symbol sequences, characterized by delays, inactive phases, and triggered markers to isolate and evaluate memory and pattern recognition capabilities. The minimality of these tasks is crucial to understand the strengths and limitations of machine learning models. Furthermore, when the input signal utilizes a one-hot encoding, ESN dynamics are governed strictly by their weight distributions, offering an ideal lens through which to study reservoir computing. Our findings map the performance boundaries of ESNs relative to state-of-the-art (SOTA) models. We show that preserving a linear state regime is vital for memory tasks, such as pattern completion or simple copy. We propose a data-dependent modulation mechanism for nonlinear input injection into the reservoir (G-ESN). G-ESN functions as a statistical filter capable of solving tasks that conventional ESNs cannot (the adding problem and bracket matching). Finally, for Deep ESNs, we evaluate a shared readout mechanism across layers that outperforms conventional concatenated readouts on structural tasks, including selective copy, sorting problem, and bracket matching.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.19997 — 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 2026-10-15T13:53:35.683Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).