Metraipolis › archive › dc_35c2b125cb73
Recognition of auditory objects from continuous and ultra-sparse spike streams in neuromorphic devices — arXiv:2610.38564
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.38564
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:58:38.374Z
- SHA-256 of the archived text
b865274c2fcdb97ab3ca93b97416b11e03df4baa3d2a4a9f339b37499021216b- Stable URL of this page
https://metraipolis.com/documento/dc_35c2b125cb73
How to cite
Recognition of auditory objects from continuous and ultra-sparse spike streams in neuromorphic devices — arXiv:2610.38564 — arXiv (en), https://arxiv.org/abs/2610.38564 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_35c2b125cb73 (Metraipolis archive dc_35c2b125cb73, sha256 b865274c2fcdb97ab3ca93b97416b11e03df4baa3d2a4a9f339b37499021216b)
BibTeX
@misc{dc35c2b125cb73,
title = {Recognition of auditory objects from continuous and ultra-sparse spike streams in neuromorphic devices — arXiv:2610.38564},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.38564},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_35c2b125cb73; sha256 b865274c2fcdb97ab3ca93b97416b11e03df4baa3d2a4a9f339b37499021216b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38564. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Energy consumption is a major concern for modern artificial intelligence (AI) applications. The brain is thought to achieve energy-efficient computation through sparse coding schemes. By emulating the spiking dynamics of the brain, neuromorphic chips hold the potential to realize energy-efficient AI. In this work, we use birdsong to demonstrate that auditory object recognition can be achieved using ultra-sparse coding. Feature-detecting neurons tuned to short temporal features ($\sim$37 ms), sampled from exemplar syllables, transform continuous auditory signals into streams of ultra-sparse spikes that mark the onsets and offsets of features within the signal. Spike patterns elicited by the exemplars are stored as templates. During recognition, template matching is performed using axonal delays between feature-detecting and template-detecting neurons. Recognition is further enhanced by an additional group of specialized binary neurons trained to discriminate between syllable categories with subtle differences. When tested on Bengalese finch songs, our approach achieved error rates below 5% using 10 to 40 exemplars per syllable type. We then implemented this recognition algorithm using spiking neural networks on Intel's neuromorphic chip, Loihi, and found that response latencies remain constant (approximately 17 ms per syllable), regardless of the number of templates used. Our results demonstrate the potential of neuromorphic chips for low-latency, low-energy recognition of complex sounds, including speech. Tema degli esploratori: scienze della vita e salute (elenco arXiv q-bio.NC, nuovi lavori del giorno). Categorie arXiv: Neurons and Cognition (q-bio.NC). Pagina del lavoro: https://arxiv.org/abs/2610.38564 — 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 2026-11-01T02:23:13.514Z dalla pagina https://arxiv.org/list/q-bio.NC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).