Metraipolis › archive › dc_e4c64ed3df6e

Predictive Suppression Layers for Communication-Efficient Spiking Neural Networks — arXiv:2609.21583

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.21583
License (as archived)
CC0-1.0
Archived
2026-10-10T01:47:33.399Z
SHA-256 of the archived text
12171e813f80516f683f4cc9c849fb0cd1e71c6ceeddaf331c45e671a64f819c
Stable URL of this page
https://metraipolis.com/documento/dc_e4c64ed3df6e

How to cite

Predictive Suppression Layers for Communication-Efficient Spiking Neural Networks — arXiv:2609.21583 — arXiv (en), https://arxiv.org/abs/2609.21583 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e4c64ed3df6e (Metraipolis archive dc_e4c64ed3df6e, sha256 12171e813f80516f683f4cc9c849fb0cd1e71c6ceeddaf331c45e671a64f819c)
BibTeX
@misc{dce4c64ed3df6e,
  title = {Predictive Suppression Layers for Communication-Efficient Spiking Neural Networks — arXiv:2609.21583},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21583},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e4c64ed3df6e; sha256 12171e813f80516f683f4cc9c849fb0cd1e71c6ceeddaf331c45e671a64f819c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21583. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Feedforward Spiking Neural Networks (SNNs) typically propagate every generated spike indiscriminately, disregarding whether the information is redundant from an information-theoretic perspective. This lack of selectivity induces high redundancy in inter-layer communication, creating an expensive overhead, e.g., in scenarios involving many-core neuromorphic hardware or communication-dominated Internet-of-Things (IoT) where features are transmitted wirelessly. To address this challenge, we trade localized processing for leaner network channels by introducing a minimal predictive coding framework for SNNs. We propose two layer variants sharing a predictor block: error units, which transmit signed spiking residuals, and predictive suppression, which uses residual magnitude to dynamically gate and forward only unpredictable, "surprising" activity. Evaluated on the N-MNIST and Spiking Heidelberg Digits (SHD) datasets using diagnostic metrics that decouple local processing from cross-layer communication, our new predictive coding layers achieve significant communication savings. Numerical results reveal a three-fold reduction in communicated activity, while increasing the task accuracy for both datasets. The latter finding is notable, and suggests that predictive coding layers not only minimize communication overhead, but also produce output feature vectors with a higher representation power.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.LG).
Categorie arXiv: Neural and Evolutionary Computing (cs.NE) ; Machine Learning (cs.LG); Signal Processing (eess.SP).
Pagina del lavoro: https://arxiv.org/abs/2609.21583 — 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 2026-10-10T01:14:16.708Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).