Metraipolis › archive › dc_510072fd37fa

Polyhedral Geometry of Time-to-First-Spike Neural Networks — arXiv:2609.11227

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.11227
License (as archived)
CC0-1.0
Archived
2026-10-16T05:54:56.750Z
SHA-256 of the archived text
093f8592c7cc3f5e9d510701e0016e8863d0f9428938f9a86c1ec12cf45fe97d
Stable URL of this page
https://metraipolis.com/documento/dc_510072fd37fa

How to cite

Polyhedral Geometry of Time-to-First-Spike Neural Networks — arXiv:2609.11227 — arXiv (en), https://arxiv.org/abs/2609.11227 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_510072fd37fa (Metraipolis archive dc_510072fd37fa, sha256 093f8592c7cc3f5e9d510701e0016e8863d0f9428938f9a86c1ec12cf45fe97d)
BibTeX
@misc{dc510072fd37fa,
  title = {Polyhedral Geometry of Time-to-First-Spike Neural Networks — arXiv:2609.11227},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11227},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_510072fd37fa; sha256 093f8592c7cc3f5e9d510701e0016e8863d0f9428938f9a86c1ec12cf45fe97d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11227. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study the expressivity of spiking neural networks, which provide a natural framework for asynchronous, event-driven computation complementary to conventional feedforward neural networks. We consider the time-to-first-spike model in a setting for which the input-output map is continuous and piecewise linear, with affine pieces governed by causal feasibility constraints that determine which presynaptic spikes occur before a neuron fires. We first show that each neuron's firing time admits a maxout-like representation with exponentially many, highly constrained affine pieces. We then formalize causal regions as polyhedral regions with fixed causal sets and derive upper and lower bounds on the maximal number of causal regions in both shallow and multilayer feedforward spiking networks. Our theoretical and experimental results show that spiking networks can generate richer partitions of the input space than conventional feedforward ReLU networks.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Combinatorics (math.CO).
Pagina del lavoro: https://arxiv.org/abs/2609.11227 — 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 2026-10-16T05:44:24.991Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).