Metraipolis › archive › dc_d62dc0cb5891

A Time-Based Readout for Vector-Matrix Multiplication in Fully Analog Memristive SNNs — arXiv:2609.11713

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.11713
License (as archived)
CC0-1.0
Archived
2026-10-16T05:27:13.589Z
SHA-256 of the archived text
5eab55508079b05eeb10fe69117aee4a775d6c7723d585fb2cc4725a302a1ce9
Stable URL of this page
https://metraipolis.com/documento/dc_d62dc0cb5891

How to cite

A Time-Based Readout for Vector-Matrix Multiplication in Fully Analog Memristive SNNs — arXiv:2609.11713 — arXiv (en), https://arxiv.org/abs/2609.11713 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d62dc0cb5891 (Metraipolis archive dc_d62dc0cb5891, sha256 5eab55508079b05eeb10fe69117aee4a775d6c7723d585fb2cc4725a302a1ce9)
BibTeX
@misc{dcd62dc0cb5891,
  title = {A Time-Based Readout for Vector-Matrix Multiplication in Fully Analog Memristive SNNs — arXiv:2609.11713},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11713},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d62dc0cb5891; sha256 5eab55508079b05eeb10fe69117aee4a775d6c7723d585fb2cc4725a302a1ce9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11713. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Artificial neural networks rely on vector-matrix multiplications (VMMs), whose implementation in von Neumann architectures is dominated by costly data movement between memory and processing units. Spiking neural networks (SNNs) mitigate this bottleneck by performing in-memory, analog VMMs using memristive crossbar arrays. However, conventional current-mode readout circuits incur significant area and power overhead. This work proposes a fully analog readout architecture based on voltage-to-time conversion of the VMM output. By sensing the column voltage, the proposed approach avoids current-mode summing and scaling circuitry, improving area and energy efficiency. Post-layout simulations of a 10x1 SNN implemented in a 130 nm CMOS technology validate the proposed architecture, while application to a trained 64x10 SNN for digit classification further demonstrates its feasibility for SNN inference.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.AI).
Categorie arXiv: Emerging Technologies (cs.ET) ; Artificial Intelligence (cs.AI); Hardware Architecture (cs.AR).
Pagina del lavoro: https://arxiv.org/abs/2609.11713 — 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 2026-10-16T05:17:52.190Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).