Metraipolis › archive › dc_72a578def321
Design and Analysis of Temporal Representations in Neural Networks — arXiv:2610.19730
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19730
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T21:58:11.355Z
- SHA-256 of the archived text
855c64bb294c80ebd4d38e87a7112223d6f565fe6a59e30bae5e09482e0b9ac1- Stable URL of this page
https://metraipolis.com/documento/dc_72a578def321
How to cite
Design and Analysis of Temporal Representations in Neural Networks — arXiv:2610.19730 — arXiv (en), https://arxiv.org/abs/2610.19730 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_72a578def321 (Metraipolis archive dc_72a578def321, sha256 855c64bb294c80ebd4d38e87a7112223d6f565fe6a59e30bae5e09482e0b9ac1)
BibTeX
@misc{dc72a578def321,
title = {Design and Analysis of Temporal Representations in Neural Networks — arXiv:2610.19730},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19730},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_72a578def321; sha256 855c64bb294c80ebd4d38e87a7112223d6f565fe6a59e30bae5e09482e0b9ac1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19730. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The ability to represent temporal information is often hypothesized to underlie the efficiency and learning capabilities of biological neural networks. This motivates the development of spiking neural networks. However, it remains unclear how temporal information is actually represented in neural networks and how different forms of temporal representation affect performance and computational efficiency. We introduce the notion of the degree of temporal representation of a neural network, defined by whether its constituent functions (activation, learning, encoding, and decoding) explicitly manipulate time as a computational variable. This perspective yields a continuum ranging from non-temporal representations, where time does not explicitly appear as a computational variable in the network functions, to fully temporal representations, where computations explicitly operate on temporal variables. Using a fixed deep architecture, we compare different encoding, activation mechanisms and decoding with increasing temporal expressiveness: non-temporal weighted-sum activations used in usual artificial neural networks, non-temporal binary spiking activations used in spiking neural networks, and spike-time-based activations used in delay neural networks. Experiments on event-based datasets show that increasing the degree of temporal representation improves both performance and computational efficiency, allowing state-of-the-art performances on the Google Speech Commands dataset. We further analyze how temporal representations induce distinct forward and backward computational trajectories, leading to gradients that depend explicitly on the history of event times. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.NE, nuovi lavori del giorno). Categorie arXiv: Neural and Evolutionary Computing (cs.NE). Pagina del lavoro: https://arxiv.org/abs/2610.19730 — 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 2026-10-15T21:39:14.499Z dalla pagina https://arxiv.org/list/cs.NE/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).