Learning nonlinear state-space models using autoencoders

DOI10.1016/j.automatica.2021.109666zbMath1478.93124OpenAlexW3158052247MaRDI QIDQ2665158

Daniele Masti, Alberto Bemporad

Publication date: 18 November 2021

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.automatica.2021.109666

zbMATH Keywords

neural networksmodel fittingidentification methodsidentification for control

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) System identification (93B30) Nonlinear systems in control theory (93C10) Model predictive control (93B45)

Related Items (5)

Optimal plug-and-control of unknown nonlinear systems ⋮ Physics-informed online learning of gray-box models by moving horizon estimation ⋮ Training recurrent neural networks by sequential least squares and the alternating direction method of multipliers ⋮ Deep subspace encoders for nonlinear system identification ⋮ On compression rate of quantum autoencoders: control design, numerical and experimental realization

Uses Software

• System Identification Toolbox
• darch
• Python
• TensorFlow
• Keras
• Spearmint
• GLIS

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Kernel methods in system identification, machine learning and function estimation: a survey
• Global optimization via inverse distance weighting and radial basis functions
• Continuous-time system identification with neural networks: model structures and fitting criteria
• Model predictive control: recent developments and future promise
• Piecewise affine regression via recursive multiple least squares and multicategory discrimination
• Reducing the Dimensionality of Data with Neural Networks
• Identification of Hammerstein systems without explicit parameterisation of non-linearity
• Universal approximation bounds for superpositions of a sigmoidal function
• Extended dynamic mode decomposition with dictionary learning: A data-driven adaptive spectral decomposition of the Koopman operator
• Nonlinear System Identification: A User-Oriented Road Map
• A Bounded-Variable Least-Squares Solver Based on Stable QR Updates
• From linear to nonlinear MPC: bridging the gap via the real-time iteration
• An Introduction to Variational Autoencoders
• Data-driven discovery of coordinates and governing equations
• A Real-Time Iteration Scheme for Nonlinear Optimization in Optimal Feedback Control
• Linearly Recurrent Autoencoder Networks for Learning Dynamics

This page was built for publication: Learning nonlinear state-space models using autoencoders