Metric entropy limits on recurrent neural network learning of linear dynamical systems

DOI10.1016/J.ACHA.2021.12.004zbMath1487.93022arXiv2105.02556OpenAlexW3159224300WikidataQ114953273 ScholiaQ114953273MaRDI QIDQ2134114

Helmut Bölcskei, Clemens Hutter, Recep Gül

Publication date: 6 May 2022

Published in: Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2105.02556

zbMATH Keywords

system identificationHardy spaceslinear dynamical systemsrecurrent neural networksmetric entropyuniversal approximation

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) System identification (93B30) Discrete-time control/observation systems (93C55) Linear systems in control theory (93C05)

Related Items (1)

Designing universal causal deep learning models: The geometric (Hyper)transformer

Uses Software

• AlphaZero
• DeepONet

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Fast projection methods for minimal design problems in linear system theory
• Approximating nonlinear fading-memory operators using neural network models
• Reconstructing a neural net from its output
• Foundations of time-frequency analysis
• Multilayer feedforward networks are universal approximators
• On the computational power of neural nets
• Neural network identifiability for a family of sigmoidal nonlinearities
• Affine symmetries and neural network identifiability
• Unconditional bases and bit-level compression
• The uncertainty principle
• On the metric complexity of casual linear systems: ε -Entropy and ε -Dimension for continuous time
• Pick's Theorem-What's the Big Deal?
• Gradient Descent Learns Linear Dynamical Systems
• High-Dimensional Statistics
• Data compression and harmonic analysis
• Deep Neural Network Approximation Theory
• Optimal Approximation with Sparsely Connected Deep Neural Networks
• Analysis of the Generalization Error: Empirical Risk Minimization over Deep Artificial Neural Networks Overcomes the Curse of Dimensionality in the Numerical Approximation of Black--Scholes Partial Differential Equations
• Introduction to Mathematical Systems Theory
• A note on metric dimension and feedback in discrete time
• Approximation by superpositions of a sigmoidal function
• Sparse components of images and optimal atomic decompositions

This page was built for publication: Metric entropy limits on recurrent neural network learning of linear dynamical systems