Metraipolis › archive › dc_eca78f735edd

Upper bounds on the number of causal pieces in spiking neural networks — arXiv:2610.22484

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.22484
License (as archived)
CC0-1.0
Archived
2026-10-19T08:42:49.948Z
SHA-256 of the archived text
1984aef116fbe70e043c545b49165415643132a1d44a4b723f5822d2797fd17b
Stable URL of this page
https://metraipolis.com/documento/dc_eca78f735edd

How to cite

Upper bounds on the number of causal pieces in spiking neural networks — arXiv:2610.22484 — arXiv (en), https://arxiv.org/abs/2610.22484 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eca78f735edd (Metraipolis archive dc_eca78f735edd, sha256 1984aef116fbe70e043c545b49165415643132a1d44a4b723f5822d2797fd17b)
BibTeX
@misc{dceca78f735edd,
  title = {Upper bounds on the number of causal pieces in spiking neural networks — arXiv:2610.22484},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22484},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eca78f735edd; sha256 1984aef116fbe70e043c545b49165415643132a1d44a4b723f5822d2797fd17b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22484. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The input space of single-spike neural networks decomposes into causal pieces, and the number of causal pieces has been shown to provide a lower bound on the approximation error for some spiking neural networks. While this decomposition is applicable to a wide range of spiking neuron models, the limits of how many causal pieces can be realised by spiking neural networks are still unknown. In this work, we derive two complementary upper bounds on the number of causal pieces in feedforward single-spike neural networks. First, we establish a combinatorial bound given by the poly-Bernoulli numbers, which applies to a broad class of spiking neuron models. The bound is of order $e^{2(L-1)N\log N+\mathcal{O}(N)}$, with network depth $L$ and maximum layer width $N$. Second, for a specific set of neuron models, we derive a bound based on hyperplane arrangements. Applying the latter framework, we obtain bounds of order $\mathcal{O}\!\left(N^{(4L-3)(N_0-1)}\right)$ for the non-leaky integrate-and-fire model with exponential synapses and the ReLU-type spike response model, and $\mathcal{O}\!\left(N^{L(N_0-1)}\right)$ for the leaky integrate-and-fire model with Dirac-$\delta$ synapses, where $N_0$ is the input dimension. For the non-leaky integrate-and-fire model with Dirac-$\delta$ synapses, additional temporal structure allows us to sharpen the general combinatorial bound to one that depends only on $N_0$, independently of the network depth and widths.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Neural and Evolutionary Computing (cs.NE) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Neurons and Cognition (q-bio.NC); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.22484 — 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 2026-10-19T08:39:10.109Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).