Neural Network Complexity of Chaos and Turbulence
arXiv:2211.15382 · doi:10.1140/epje/s10189-023-00321-7
Abstract
Chaos and turbulence are complex physical phenomena, yet a precise definition of the complexity measure that quantifies them is still lacking. In this work we consider the relative complexity of chaos and turbulence from the perspective of deep neural networks. We analyze a set of classification problems, where the network has to distinguish images of fluid profiles in the turbulent regime from other classes of images such as fluid profiles in the chaotic regime, various constructions of noise and real world images. We analyze incompressible as well as weakly compressible fluid flows. We quantify the complexity of the computation performed by the network via the intrinsic dimensionality of the internal feature representations, and calculate the effective number of independent features which the network uses in order to distinguish between classes. In addition to providing a numerical estimate of the complexity of the computation, the measure also characterizes the neural network processing at intermediate and final stages. We construct adversarial examples and use them to identify the two point correlation spectra for the chaotic and turbulent vorticity as the feature used by the network for classification.
References in corpus (11)
- Towards A Rigorous Science of Interpretable Machine Learning
- A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstruction
- Growing condensate in two-dimensional turbulence
- Fantastic Generalization Measures and Where to Find Them
- AdS/CFT as a deep Boltzmann machine
- Reconstructing velocity and pressure from sparse noisy particle tracks using Physics-Informed Neural Networks
- Generative Modeling of Turbulence
- Self-similar Subgrid-scale Models for Inertial Range Turbulence and Accurate Measurements of Intermittency
- Numerical Measurements of Scaling Relations in Two-Dimensional Conformal Fluid Turbulence
- Conformal invariance of weakly compressible two-dimensional turbulence
- Semi-supervised Learning of Partial Differential Operators and Dynamical Flows