Metraipolis › archive › dc_7f9527d83eeb
Frequency Selective Neural Networks as a Foundation Architecture for Time Series Learning — arXiv:2608.29012
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29012
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:43:58.708Z
- SHA-256 of the archived text
8dcfe07bd8cf00ec04936f3207ddcbe78fb3a7eb38d3602bac7150d2a3fa6921- Stable URL of this page
https://metraipolis.com/documento/dc_7f9527d83eeb
How to cite
Frequency Selective Neural Networks as a Foundation Architecture for Time Series Learning — arXiv:2608.29012 — arXiv (en), https://arxiv.org/abs/2608.29012 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7f9527d83eeb (Metraipolis archive dc_7f9527d83eeb, sha256 8dcfe07bd8cf00ec04936f3207ddcbe78fb3a7eb38d3602bac7150d2a3fa6921)
BibTeX
@misc{dc7f9527d83eeb,
title = {Frequency Selective Neural Networks as a Foundation Architecture for Time Series Learning — arXiv:2608.29012},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29012},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7f9527d83eeb; sha256 8dcfe07bd8cf00ec04936f3207ddcbe78fb3a7eb38d3602bac7150d2a3fa6921},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29012. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Time-series data across physical and biological domains are fundamentally driven by complex, non-stationary oscillatory modes. While deep learning models, such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks, and Transformers, have dominated sequential analysis, they remain fundamentally "spectral-blind". By mapping continuous physical waves into unconstrained spatial or discrete token spaces, these architectures suffer from severe spectral entanglement, acting as opaque black boxes that decouple predictive accuracy from physical reality. In this paper, we introduce the Frequency Selective Neural Network (FSNN), pioneering a foundation architecture guaranteeing physical interpretability without sacrificing expressive power of deep learning. FSNN addresses spectral entanglement by explicitly embedding the rigorous mathematics of advanced signal processing into its neural topology. Through a fully differentiable Wiener-like filter bank optimized via complex-domain backpropagation, FSNN autonomously discovers and isolates the precise physical modes of a given task. Extensive evaluations demonstrate that FSNN establishes state-of-the-art predictive performance, achieving $77.0\%$ average accuracy on the standard 10 multivariate UEA datasets and leading across all major metrics on the highly imbalanced PTB-XL clinical ECG benchmark. Crucially, in contrast to yielding abstract feature maps, FSNN converges directly on physically meaningful frequency bands, such as isolating the cardiac QRS complex, providing a highly scalable, interpretable paradigm for robust pattern recognition in complex temporal domains. Our code is available at: this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.29012 — 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 2026-10-17T07:28:26.500Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).