Neural networks have the ability to serve as universal function approximators, but they are not interpretable and do not generalize well outside of their training region. Both of these issues are problematic when trying to apply standard neural ordinary differential equations (ODEs) to dynamical systems. We introduce the polynomial neural ODE, which is a deep polynomial neural network inside of the neural ODE framework. We demonstrate the capability of polynomial neural ODEs to predict outside of the training region, as well as to perform direct symbolic regression without using additional tools such as SINDy.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10076068 | PMC |
| http://dx.doi.org/10.1063/5.0130803 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A Joint three-plane Physics-constrained Deep learning based Polynomial Fitting Approach for MR Electrical Properties Tomography.
Neuroimage
January 2025
Department of Electrical and Electronic Engineering, Yonsei University, Seoul, Republic of Korea. Electronic address:
Magnetic resonance electrical properties tomography can extract the electrical properties of in-vivo tissue. To estimate tissue electrical properties, various reconstruction algorithms have been proposed. However, physics-based reconstructions are prone to various artifacts such as noise amplification and boundary artifact.
View Article and Find Full Text PDFPhysics-informed Neural Implicit Flow neural network for parametric PDEs.
Neural Netw
January 2025
Defense Innovation Institute, Chinese Academy of Military Science, Beijing 100071, China; Intelligent Game and Decision Laboratory, China.
The Physics-informed Neural Network (PINN) has been a popular method for solving partial differential equations (PDEs) due to its flexibility. However, PINN still faces challenges in characterizing spatio-temporal correlations when solving parametric PDEs due to network limitations. To address this issue, we propose a Physics-Informed Neural Implicit Flow (PINIF) framework, which enables a meshless low-rank representation of the parametric spatio-temporal field based on the expressiveness of the Neural Implicit Flow (NIF), enabling a meshless low-rank representation.
View Article and Find Full Text PDFEnhanced Disc Herniation Classification Using Grey Wolf Optimization Based on Hybrid Feature Extraction and Deep Learning Methods.
Tomography
December 2024
Department of Computer Engineering, Faculty of Engineering, Karabük University, Karabük 78050, Türkiye.
Unlabelled: Due to the increasing number of people working at computers in professional settings, the incidence of lumbar disc herniation is increasing.
Background/objectives: The early diagnosis and treatment of lumbar disc herniation is much more likely to yield favorable results, allowing the hernia to be treated before it develops further. The aim of this study was to classify lumbar disc herniations in a computer-aided, fully automated manner using magnetic resonance images (MRIs).
Shannon Entropy Computations in Navier-Stokes Flow Problems Using the Stochastic Finite Volume Method.
Entropy (Basel)
January 2025
Faculty of Civil Engineering, Architecture and Environmental Engineering, Lodz University of Technology, 90-924 Łódź, Poland.
The main aim of this study is to achieve the numerical solution for the Navier-Stokes equations for incompressible, non-turbulent, and subsonic fluid flows with some Gaussian physical uncertainties. The higher-order stochastic finite volume method (SFVM), implemented according to the iterative generalized stochastic perturbation technique and the Monte Carlo scheme, are engaged for this purpose. It is implemented with the aid of the polynomial bases for the pressure-velocity-temperature (PVT) solutions, for which the weighted least squares method (WLSM) algorithm is applicable.
View Article and Find Full Text PDFThe application of design of experiments and artificial neural networks in the evaluation of the impact of acidic conditions on cloud point extraction.
J Chromatogr A
January 2025
Department of Physical Pharmacy and Pharmacokinetics, Poznań University of Medical Sciences, Rokietnicka 3 Street, Poznań 60-806, Poland. Electronic address:
This study aimed to analyze the impact of acidic conditions on the recovery of ciprofloxacin and levofloxacin for cloud point extraction with the Design of Experiments and Artificial Neural Networks. The design included 27 experiments featuring three repetitions of the central point for both drugs. The tested parameters included Triton X-114 concentration, HCl concentration, NaCl concentration, and incubation temperature, which were coded at five levels.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!