Piecewise integrable neural network: an interpretable chaos identification framework

DOI10.1063/5.0134984MaRDI QIDQ6572660

Nico Novelli, Stefano Lenci, Pierpaolo Belardinelli

Publication date: 16 July 2024

Published in: Chaos (Search for Journal in Brave)

Mathematics Subject Classification ID

Dynamical systems and ergodic theory (37-XX) Ordinary differential equations (34-XX)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Hamiltonian systems and transformations in Hilbert space.
• On the relation between Rayleigh-Bénard convection and Lorenz system
• Turing computability with neural nets
• Approximation rates for neural networks with general activation functions
• The universal approximation property. Characterization, construction, representation, and existence
• Approximation spaces of deep neural networks
• Universal approximations of invariant maps by neural networks
• On dynamic mode decomposition: theory and applications
• Piecewise affine models of chaotic attractors: The Rössler and Lorenz systems
• Universal approximation bounds for superpositions of a sigmoidal function
• Strong universal consistency of neural network classifiers
• Unpredictability and undecidability in dynamical systems
• Analysis of Fluid Flows via Spectral Properties of the Koopman Operator
• A Lorenz-type attractor in a piecewise-smooth system: Rigorous results
• Equivalence of approximation by convolutional neural networks and fully-connected networks
• An in-depth numerical study of the two-dimensional Kuramoto–Sivashinsky equation
• Approximation by superpositions of a sigmoidal function

Related Items (2)

The identification of piecewise non-linear dynamical system without understanding the mechanism ⋮ Electromagnetic radiation control for nonlinear dynamics of Hopfield neural networks

This page was built for publication: Piecewise integrable neural network: an interpretable chaos identification framework