EUVIMEDEUVIMED entdecken
Crossref

Dynamic Inference Limits in Plastic Recurrent Networks Under Invasive Measurement

Davide Anniballi

Neural Computation · 10.11.2026 · 38 (12) · 2169-2223

DOI: 10.1162/neco.a.1593 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Neural Computation, online erschienen am 10.11.2026. Verfasst von Davide Anniballi. Beteiligte Einrichtung: Independent researcher, Pesaro, Italy davideanniballi@gmail.com. Die Arbeit nennt 29 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We derive a lower bound on the error of parameter inference from invasive measurement in recurrent adaptive networks with online plasticity. The bound decomposes into a variance contribution and a bias contribution, arising from physically distinct components of measurement back-action: stochastic fluctuations injected into the state dynamics and the systematic shift of the state operating point under repeated observation. Under generic measurement families, the bias term and the measurement-dependent component of the variance channel increase with measurement precision through distinct mechanisms and cannot generally be traded off against each other. Near marginal stability, both contributions are amplified by resolvent operators that diverge as their corresponding spectral radii approach unity, so that the bound becomes more restrictive in the regime in which cortical circuits are believed to operate. Evaluated at biologically realistic scale, the bound implies that the per-neuron disturbance required for noninvasiveness falls orders of magnitude below ambient biological fluctuations, making the constraint plausibly operative for standard invasive measurement modalities. Beyond the stationary regime, a finite-time analysis converts the bound into an experimentally relevant timescale, distinguishing the ballistic accumulation of measurement-induced bias from intrinsic representational drift and yielding testable temporal and geometric signatures for optogenetic and chronic-recording protocols. The result identifies a structural limit on parameter inference in adaptive recurrent systems, induced by the dynamical coupling between measurement, recurrent amplification, and online plasticity.

Autor:innen und Institutionen

  • Independent researcher, Pesaro, Italy davideanniballi@gmail.com.

Zitieren

APA

Anniballi, D. (2026). Dynamic Inference Limits in Plastic Recurrent Networks Under Invasive Measurement. Neural Computation, 38(12), 2169-2223. https://doi.org/10.1162/neco.a.1593

Vancouver

Anniballi D. Dynamic Inference Limits in Plastic Recurrent Networks Under Invasive Measurement. Neural Computation. 2026;38(12):2169-2223. doi:10.1162/neco.a.1593

BibTeX
@article{Anniballi2026,
  author = {Anniballi, Davide},
  title = {Dynamic Inference Limits in Plastic Recurrent Networks Under Invasive Measurement},
  journal = {Neural Computation},
  year = {2026},
  volume = {38},
  number = {12},
  pages = {2169--2223},
  doi = {10.1162/neco.a.1593}
}
Kostenlos starten →