Metraipolis › archive › dc_fa0f22263c69
Activation-Flexible ANN-to-SNN Conversion with Finite-State Markov Neurons — arXiv:2609.30102
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30102
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T07:23:44.672Z
- SHA-256 of the archived text
c11e20df63daaebabe88b8b7ca3ccadafbd69fd74694fe1241a9c5710160acb3- Stable URL of this page
https://metraipolis.com/documento/dc_fa0f22263c69
How to cite
Activation-Flexible ANN-to-SNN Conversion with Finite-State Markov Neurons — arXiv:2609.30102 — arXiv (en), https://arxiv.org/abs/2609.30102 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fa0f22263c69 (Metraipolis archive dc_fa0f22263c69, sha256 c11e20df63daaebabe88b8b7ca3ccadafbd69fd74694fe1241a9c5710160acb3)
BibTeX
@misc{dcfa0f22263c69,
title = {Activation-Flexible ANN-to-SNN Conversion with Finite-State Markov Neurons — arXiv:2609.30102},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30102},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fa0f22263c69; sha256 c11e20df63daaebabe88b8b7ca3ccadafbd69fd74694fe1241a9c5710160acb3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30102. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Most ANN-to-SNN conversion methods rely on a specific correspondence between the source activation and the spiking neuron dynamics. We propose a finite-state continuous-time Markov chain (CTMC) neuron framework whose stationary spike flux can approximate every continuous nonnegative monotone activation function on a compact interval. For a generalized CTMC family with affine input-dependent transitions, we prove uniform approximation to arbitrary accuracy over this function class and derive an explicit approximation error bound. In practice, two- and three-state CTMCs fit ReLU, sigmoid, softplus, and clipped ReLU on the evaluated input ranges, and we evaluate corresponding MLP conversions for each activation with layerwise rate scaling. Moderate clipping improves the conversion cost-accuracy tradeoff on the MNIST MLP and reduces SynOps by 27% on VGG-11/MNIST at matched ANN-SNN accuracy gap criteria, whereas the trend reverses on VGG-11/CIFAR-10. Mean-field and layerwise diagnostics indicate that finite-window sampling and terminal-layer mismatch are the main residual errors. Overall, our results establish finite-state CTMC neurons as a theoretically grounded framework for activation-flexible ANN-to-SNN conversion beyond fixed activation-neuron correspondences. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.NE). Categorie arXiv: Neural and Evolutionary Computing (cs.NE). Pagina del lavoro: https://arxiv.org/abs/2609.30102 — 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 2026-10-08T06:43:56.390Z dalla pagina https://arxiv.org/catchup/cs.NE/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).