Results 41 to 50 of about 13,405 (259)

h-Analysis and data-parallel physics-informed neural networks

Scientific Reports, 2023
We explore the data-parallel acceleration of physics-informed machine learning (PIML) schemes, with a focus on physics-informed neural networks (PINNs) for multiple graphics processing units (GPUs) architectures. In order to develop scale-robust and high-
Paul Escapil-Inchauspé, Gonzalo A. Ruz
doaj   +1 more source

Physics-Informed Deep Neural Operator Networks

, 2023
33 pages, 14 figures.
Goswami, Somdatta, Bora, Aniruddha, Yu, Yue, Karniadakis, George Em   +3 more
openaire   +2 more sources

Digital twins to accelerate target identification and drug development for immune‐mediated disorders

FEBS Open Bio, EarlyView.
Digital twins integrate patient‐derived molecular and clinical data into personalised computational models that simulate disease mechanisms. They enable rapid identification and validation of therapeutic targets, prediction of drug responses, and prioritisation of candidate interventions.
Anna Niarakis, Philippe Moingeon
wiley   +1 more source

SPIKANs: separable physics-informed Kolmogorov–Arnold networks

Machine Learning: Science and Technology
Physics-Informed Neural Networks (PINNs) have emerged as a promising method for solving partial differential equations (PDEs) in scientific computing.
Bruno Jacob, Amanda A Howard, Panos Stinis   +2 more
doaj   +1 more source

Physics-Informed Deep Neural Networks for Transient Electromagnetic Analysis

IEEE Open Journal of Antennas and Propagation, 2020
In this paper, we propose a deep neural network based model to predict the time evolution of field values in transient electrodynamics. The key component of our model is a recurrent neural network, which learns representations of long-term spatial ...
Oameed Noakoasteen, Shu Wang, Zhen Peng, Christos Christodoulou   +3 more
doaj   +1 more source

Physics-Informed Classical Lagrange / Hamilton Neural Networks in Deep Learning

Современные информационные технологии и IT-образование, 2022
The principles of constructing deep machine learning systems based on taking into account information about the physical properties of the studied control object, such as an autonomous robot, are considered.
Daria Zrelova, Sergey Ulyanov
doaj   +1 more source

Visual Recovery Reflects Cortical MeCP2 Sensitivity in Rett Syndrome

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Objective Rett syndrome (RTT) is a devastating neurodevelopmental disorder with developmental regression affecting motor, sensory, and cognitive functions. Sensory disruptions contribute to the complex behavioral and cognitive difficulties and represent an important target for therapeutic interventions.
Alex Joseph Simon, Nathalie Picard, Valeria d'Andrea, Enchi Chang, Joseph Leffler, Eleonora Centofante, Matthew Taylor, Francesca Bardi, Francesca Cavicchiolo, Takao K. Hensch, Stefano Panzeri, Chinfei Chen, Michela Fagiolini   +12 more
wiley   +1 more source

MT-PINNs: multi-term physics-informed neural networks for solving initial boundary value problems of 2D and 3D nonlinear telegraph equations

Boundary Value Problems
The nonlinear telegraph equation appears in a variety of engineering and science problems. This paper presents a deep learning algorithm termed multi-term physics-informed neural networks to resolve initial boundary value problems of 2D and 3D hyperbolic
Alemayehu Tamirie Deresse, Alemu Senbeta Bekela, Tamirat Temesgen Dufera   +2 more
doaj   +1 more source

Network Localization of Fatigue in Multiple Sclerosis

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Background Fatigue is among the most common symptoms and one of the main factors determining the quality of life in multiple sclerosis (MS). However, the neurobiological mechanisms underlying fatigue are not fully understood. Here we studied lesion locations and their connections in individuals with MS, aiming to identify brain networks ...
Olli Likitalo, Jaakko Kungshamn, Albert Bellmunt‐Gil, Silvia Tommasin, Abhineet Ojha, Matias Viitala, Juho Aaltonen, Jyrki Lötjönen, Juha Koikkalainen, Pauli Ylikotila, Patrizia Pantano, Merja Soilu‐Hänninen, Juho Joutsa   +12 more
wiley   +1 more source

Theory-informed neural networks for particle physics

Machine Learning: Science and Technology
We present a theory-informed reinforcement-learning framework that recasts the combinatorial assignment of final-state particles in hadron collider events as a Markov decision process.
Barry M Dillon, Michael Spannowsky
doaj   +1 more source