Exploiting the capacity of deep networks only at the training stage for nonlinear black-box system identification

DOI10.1016/J.INS.2024.121351zbMATH Open1548.93029MaRDI QIDQ6608330FDOQ6608330

Authors: Vahid MohammadZadeh Eivaghi, Mahdi Aliyari Shoorehdeli 

Publication date: 19 September 2024

Published in: Information Sciences (Search for Journal in Brave)

Recommendations

• Deep networks for system identification: a survey
• Sparse Bayesian deep learning for dynamic system identification
• Learning nonlinear state-space models using autoencoders
• Continuous-time system identification with neural networks: model structures and fitting criteria
• Deep subspace encoders for nonlinear system identification

zbMATH Keywords

nonlinear system identificationalgorithmic transparencydeep generative modelscontrastive learning

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) System identification (93B30) Nonlinear systems in control theory (93C10)

Cites Work

• Pattern recognition and machine learning.
• Deep learning
• Subspace methods for system identification.
• A Fast Learning Algorithm for Deep Belief Nets
• Nonlinear system identification. From classical approaches to neural networks, fuzzy models, and Gaussian processes
• Nonlinear System Identification: A User-Oriented Road Map
• Learning nonlinear state-space models using autoencoders
• Sparse Bayesian deep learning for dynamic system identification
• \textit{dynoNet}: a neural network architecture for learning dynamical systems

This page was built for publication: Exploiting the capacity of deep networks only at the training stage for nonlinear black-box system identification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6608330)