Metraipolis › archive › dc_87ca97c89044

Beyond Low-Pass Dynamics: Frequency-Selective Spiking Reservoirs with Resonant Neurons — arXiv:2610.37906

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.37906
License (as archived)
CC0-1.0
Archived
2026-10-31T06:08:41.169Z
SHA-256 of the archived text
2e4957b61dcc43a98e3455f8ddb96b5a388cbed075fb018de57d24603cff508d
Stable URL of this page
https://metraipolis.com/documento/dc_87ca97c89044

How to cite

Beyond Low-Pass Dynamics: Frequency-Selective Spiking Reservoirs with Resonant Neurons — arXiv:2610.37906 — arXiv (en), https://arxiv.org/abs/2610.37906 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_87ca97c89044 (Metraipolis archive dc_87ca97c89044, sha256 2e4957b61dcc43a98e3455f8ddb96b5a388cbed075fb018de57d24603cff508d)
BibTeX
@misc{dc87ca97c89044,
  title = {Beyond Low-Pass Dynamics: Frequency-Selective Spiking Reservoirs with Resonant Neurons — arXiv:2610.37906},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.37906},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_87ca97c89044; sha256 2e4957b61dcc43a98e3455f8ddb96b5a388cbed075fb018de57d24603cff508d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.37906. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Spiking reservoir computing combines the training efficiency of fixed recurrent reservoirs with the energy efficiency of event-driven inference, where computation is triggered by sparse spikes rather than executed densely at every timestep. However, existing spiking reservoirs almost exclusively rely on Leaky Integrate-and-Fire (LIF) neurons, whose low-pass dynamics limit their ability to distinguish information encoded at different temporal frequencies. We introduce HRF-Res, a liquid state machine in which LIF neurons are replaced by a heterogeneous population of Harmonic Resonate-and-Fire (HRF) neurons. These neurons exhibit intrinsic oscillatory dynamics and selectively respond to input frequencies, enabling the reservoir to capture frequency-specific temporal patterns. The result is more discriminative representations and higher classification accuracy than LIF-based reservoirs, achieved without sacrificing the energy efficiency of spiking computation, with up to 19x lower energy consumption than an equivalent non-spiking oscillatory reservoir. Evaluated on ten benchmarks spanning time series, sequential images, audio spike trains, and neuromorphic vision, HRF-Res achieves state-of-the-art accuracy among spiking reservoir methods. These results demonstrate that introducing frequency-selective dynamics into spiking reservoirs improves representational quality and classification performance while preserving their inherent energy efficiency.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.37906 — 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 2026-10-31T06:07:08.438Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).