Data-driven performance metrics for neural network learning

DOI10.1002/ACS.3701MaRDI QIDQ6859507zbMATH OpenFDO

Authors A. Alessandri, Mauro Gaggero, Marcello Sanguineti

Publication date 12 February 2026

Published in International Journal of Adaptive Control and Signal Processing (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1002/ACS.3701

zbMATH Keywords

extended Kalman filterfeedforward neural networkslocal minimaneural learningperformance metricsCramér-Rao bound

Mathematics Subject Classification ID

Systems theory; control (93-XX)

Cites work

• scientific article; zbMATH DE number 1243473 (Why is no real title available?)
• scientific article; zbMATH DE number 1405266 (Why is no real title available?)
• A recursive algorithm for nonlinear least-squares problems
• Approximate minimization of the regularized expected error over kernel models
• Comparing fixed and variable-width Gaussian networks
• Dependence of Computational Models on Input Dimension: Tractability of Approximation and Optimization Tasks
• Filtering, predictive, and smoothing Cramér-Rao bounds for discrete-time nonlinear dynamic systems
• LQG online learning
• Low-discrepancy sampling for approximate dynamic programming with local approximators
• Oscillation and chaos in physiological control systems
• Statistical Methods for Data Analysis
• Universal approximation bounds for superpositions of a sigmoidal function

Cited in

(2)

• Data-driven forecasting of ship motions in waves using machine learning and dynamic mode decomposition
• Editorial. Reduced-order, data-driven, and decomposition methods for modelling, identification, and estimation

This page was built for publication: Data-driven performance metrics for neural network learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6859507)