English
Related papers

Related papers: Locally-symplectic neural networks for learning vo…

200 papers

In this note, we propose a symplectic algorithm for the stable manifolds of the Hamilton-Jacobi equations combined with an iterative procedure in [Sakamoto-van~der Schaft, IEEE Transactions on Automatic Control, 2008]. Our algorithm…

Optimization and Control · Mathematics 2021-08-16 Guoyuan Chen , Gaosheng Zhu

We present an approach to construct appropriate and efficient emulators for Hamiltonian flow maps. Intended future applications are long-term tracing of fast charged particles in accelerators and magnetic plasma confinement configurations.…

Computational Physics · Physics 2021-06-02 Katharina Rath , Christopher G. Albert , Bernd Bischl , Udo von Toussaint

Natural spatiotemporal processes can be highly non-stationary in many ways, e.g. the low-level non-stationarity such as spatial correlations or temporal dependencies of local pixel values; and the high-level variations such as the…

Machine Learning · Computer Science 2019-04-23 Yunbo Wang , Jianjin Zhang , Hongyu Zhu , Mingsheng Long , Jianmin Wang , Philip S Yu

The phenomenon of linear mode connectivity (LMC) links several aspects of deep learning, including training stability under noisy stochastic gradients, the smoothness and generalization of local minima (basins), the similarity and…

Machine Learning · Computer Science 2025-11-07 C. Hepburn , T. Zielke , A. P. Raulf

Many consequential real-world systems, like wind fields and ocean currents, are dynamic and hard to model. Learning their governing dynamics remains a central challenge in scientific machine learning. Dynamic Mode Decomposition (DMD)…

Machine Learning · Computer Science 2025-11-26 Yujin Kim , Sarah Dean

We propose a neural entropy-stable conservative flux form neural network (NESCFN) for learning hyperbolic conservation laws and their associated entropy functions directly from solution trajectories, without requiring any predefined…

Numerical Analysis · Mathematics 2025-07-03 Lizuo Liu , Lu Zhang , Anne Gelb

We use parsimonious diffusion maps (PDMs) to discover the latent dynamics of high-fidelity Navier-Stokes simulations with a focus on the 2D fluidic pinball problem. By varying the Reynolds number, different flow regimes emerge, ranging from…

Fluid Dynamics · Physics 2024-11-05 Alessandro Della Pia , Dimitris Patsatzis , Lucia Russo , Constantinos Siettos

Fluid prediction is a long-standing challenge due to the intrinsic high-dimensional non-linear dynamics. Previous methods usually utilize the non-linear modeling capability of deep models to directly estimate velocity fields for future…

Machine Learning · Computer Science 2024-06-10 Lanxiang Xing , Haixu Wu , Yuezhou Ma , Jianmin Wang , Mingsheng Long

Deep learning-based lossless compression methods offer substantial advantages in compressing medical volumetric images. Nevertheless, many learning-based algorithms encounter a trade-off between practicality and compression performance.…

Image and Video Processing · Electrical Eng. & Systems 2023-11-29 Qianhao Chen , Jietao Chen

In this paper, we introduce the notion of liquid time-constant (LTC) recurrent neural networks (RNN)s, a subclass of continuous-time RNNs, with varying neuronal time-constant realized by their nonlinear synaptic transmission model. This…

Machine Learning · Computer Science 2018-11-02 Ramin M. Hasani , Mathias Lechner , Alexander Amini , Daniela Rus , Radu Grosu

In this paper, the prediction capabilities of recurrent neural networks are assessed in the low-order model of near-wall turbulence by Moehlis {\it et al.} (New J. Phys. {\bf 6}, 56, 2004). Our results show that it is possible to obtain…

Invariants and conservation laws convey critical information about the underlying dynamics of a system, yet it is generally infeasible to find them from large-scale data without any prior knowledge or human insight. We propose ConservNet to…

Machine Learning · Computer Science 2021-07-01 Seungwoong Ha , Hawoong Jeong

We reveal the symplectic nature of parameter-drift maps by embedding them into extended phase space. Applying the embedding to the parameter-drift standard nontwist map, our construction yields an autonomous symplectic map in extended phase…

Chaotic Dynamics · Physics 2025-05-09 Gabriel C. Grime , Philip J. Morrison

Shunting inhibitory cellular neural networks (SICNNs) with continuous as well as discontinuous external inputs are investigated. The descriptions of homoclinic and heteroclinic motions are provided in the functional sense for the…

Chaotic Dynamics · Physics 2016-09-23 Mehmet Onur Fen , Fatma Tokmak Fen

The computational capabilities of a neural network are widely assumed to be determined by its static architecture. Here we challenge this view by establishing that a fixed neural structure can operate in fundamentally different…

Neural and Evolutionary Computing · Computer Science 2025-09-24 Xia Chen

A number of techniques have been developed to perturb the dynamics of $C^1$-diffeomorphisms and to modify the properties of their periodic orbits. For instance, one can locally linearize the dynamics, change the tangent dynamics, or create…

Dynamical Systems · Mathematics 2017-09-13 Jerome Buzzi , Sylvain Crovisier , Todd Fisher

We consider some differential geometric classes of local and nonlocal Poisson and symplectic structures on loop spaces of smooth manifolds which give natural Hamiltonian and multihamiltonian representations for some important nonlinear…

High Energy Physics - Theory · Physics 2016-09-06 Oleg Mokhov

We propose a deep probabilistic-neural-network architecture for learning a minimal and near-orthogonal set of non-linear modes from high-fidelity turbulent-flow-field data useful for flow analysis, reduced-order modeling, and flow control.…

Fluid Dynamics · Physics 2021-09-06 Hamidreza Eivazi , Soledad Le Clainche , Sergio Hoyas , Ricardo Vinuesa

Stochastic gradient methods are dominant in nonconvex optimization especially for deep models but have low asymptotical convergence due to the fixed smoothness. To address this problem, we propose a simple yet effective method for improving…

Machine Learning · Computer Science 2018-05-25 Jun Li , Hongfu Liu , Bineng Zhong , Yue Wu , Yun Fu

This thesis deals with neural networks that respect symmetries and presents the advantages in applying them to lattice field theory problems. The concept of equivariance is explained, together with the reason why such a property is crucial…

High Energy Physics - Lattice · Physics 2025-06-17 Matteo Favoni