Metraipolis › archive › dc_346c064bdc2e

On the Number of Observation Nodes in Recurrent Neural Networks with Linear Threshold and ReLU Functions — arXiv:2608.29650

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29650
License (as archived)
CC0-1.0
Archived
2026-10-17T10:42:17.117Z
SHA-256 of the archived text
b600ea9369d41ed28d7ca9b3221859ef74c1a3a8468613fd88ed6b80646b348c
Stable URL of this page
https://metraipolis.com/documento/dc_346c064bdc2e

How to cite

On the Number of Observation Nodes in Recurrent Neural Networks with Linear Threshold and ReLU Functions — arXiv:2608.29650 — arXiv (en), https://arxiv.org/abs/2608.29650 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_346c064bdc2e (Metraipolis archive dc_346c064bdc2e, sha256 b600ea9369d41ed28d7ca9b3221859ef74c1a3a8468613fd88ed6b80646b348c)
BibTeX
@misc{dc346c064bdc2e,
  title = {On the Number of Observation Nodes in Recurrent Neural Networks with Linear Threshold and ReLU Functions — arXiv:2608.29650},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29650},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_346c064bdc2e; sha256 b600ea9369d41ed28d7ca9b3221859ef74c1a3a8468613fd88ed6b80646b348c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29650. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper investigates how node update rules and admissible state domains affect the minimum number of observation nodes required for global finite-horizon observability in recurrent neural networks with linear-threshold and ReLU update functions. Over a common binary state domain, we construct a class of $K$-linear-threshold ($K$-LT) networks whose initial states can be uniquely reconstructed from the finite output trajectory of a single observation node. We further establish a dynamical equivalence between binary-valued $K$-ReLU networks and $K$-AND Boolean networks, which transfers existing class-level observation-node bounds to binary-valued $K$-ReLU networks. For nonnegative-valued ReLU networks, the observability problem reduces to the classical linear-system setting whenever the relevant pre-activations remain nonnegative. For general real-valued ReLU networks, we prove that global finite-horizon observability requires at least $n/2$ observation nodes when no restriction is imposed on the number of state variables involved in each node update. This lower bound is tight when $n=2K$, for which we construct a $K$-ReLU network observable from exactly $K$ nodes. These results show that both update rules and state domains fundamentally affect extremal observation requirements: temporal evolution can concentrate finite-state information into a single measured trajectory, whereas activation-induced rank loss creates an intrinsic sensor lower bound in continuous-state ReLU networks.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-01 in eess.SY).
Categorie arXiv: Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2608.29650 — 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 2026-10-17T10:29:43.040Z dalla pagina https://arxiv.org/catchup/eess.SY/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).