Metraipolis › archive › dc_d9a5fb667aba
Input-dependent Neuromodulation Enhances Mixed-Signal Neuromorphic Hardware — arXiv:2610.41265
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41265
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T08:23:42.603Z
- SHA-256 of the archived text
0329aaf0d118d5d5d4ffe75b83b4343fc2d852ecdf268992ecfce4794ca36bc4- Stable URL of this page
https://metraipolis.com/documento/dc_d9a5fb667aba
How to cite
Input-dependent Neuromodulation Enhances Mixed-Signal Neuromorphic Hardware — arXiv:2610.41265 — arXiv (en), https://arxiv.org/abs/2610.41265 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d9a5fb667aba (Metraipolis archive dc_d9a5fb667aba, sha256 0329aaf0d118d5d5d4ffe75b83b4343fc2d852ecdf268992ecfce4794ca36bc4)
BibTeX
@misc{dcd9a5fb667aba,
title = {Input-dependent Neuromodulation Enhances Mixed-Signal Neuromorphic Hardware — arXiv:2610.41265},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41265},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d9a5fb667aba; sha256 0329aaf0d118d5d5d4ffe75b83b4343fc2d852ecdf268992ecfce4794ca36bc4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41265. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Gating mechanisms allow a fixed neural network to adapt its computation to the current input by dynamically modulating its effective parameters. In the brain, neuromodulation uses this principle to move neural circuits between dynamical regimes, and deep learning exploits input-dependent gating, e.g., in gated recurrent networks and self-attention. Input-dependent modulation has also recently been shown to improve spiking neural networks, with particularly strong benefits in small, parameter-limited ones. This makes neuromodulation especially promising for neuromorphic processors at the edge, where area, memory and energy budgets constrain network size, while circuit physics limits parameter precision. Here we demonstrate input-dependent, within-trial neuromodulation of a spiking recurrent neural network on a mixed-signal neuromorphic processor. An off-chip modulator reads the on-chip network's input and activity and adjusts its population-level gains while the chip's analog circuits compute with the physics of the silicon. Neuromodulation raises binary spoken-digit classification accuracy by $+17.3 \pm 10.4$ percentage points, tested across five hardware network instantiations. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.NE, nuovi lavori del giorno). Categorie arXiv: Neural and Evolutionary Computing (cs.NE) ; Emerging Technologies (cs.ET). Pagina del lavoro: https://arxiv.org/abs/2610.41265 — 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 2026-11-03T08:07:23.783Z dalla pagina https://arxiv.org/list/cs.NE/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).