Results 131 to 140 of about 29,946 (302)

Dual-Balancing for Physics-Informed Neural Networks

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence
Physics-informed neural networks (PINNs) have emerged as a new learning paradigm for solving partial differential equations (PDEs) by enforcing the constraints of physical equations, boundary conditions (BCs), and initial conditions (ICs) into the loss function. Despite their successes, vanilla PINNs still suffer from poor accuracy and slow convergence
Chenhong Zhou, Jie Chen 0026, Zaifeng Yang, Ching Eng Png   +3 more
openaire   +2 more sources

Nonlinear interaction in composites using physics informed neural networks [PDF]

Modelling of composites requires the consideration of various components that work together and interact in a linear and nonlinear way. Linear and nonlinear modelling in view of demanding needs, like representative volume element calculations within ...
Drosopoulos, Georgios, Stavroulakis, Georgios E., Mouratidou, Aliki   +2 more
core   +3 more sources

Advancing deformation calculation: a physics-informed deep graph learning framework for hyperelastic materials

Advanced Modeling and Simulation in Engineering Sciences
In elastohydrodynamic lubrication (EHL) simulations, classical numerical methods like the finite difference method (FDM) and the finite element method (FEM) are commonly employed. While PINNs have proven to be a suitable alternative for fluid simulation,
Faras Brumand-Poor, Matthias Trautmann, Katharina Schmitz   +2 more
doaj   +1 more source

Loss-attentional physics-informed neural networks

Journal of Computational Physics
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Song, Y., Wang, H., Yang, H., Taccari, M.L., Chen, X.   +4 more
openaire   +3 more sources

Transparent and Robust LiCl–Organohydrogel Triboelectric Nanogenerator With Deep Learning Assisted Sensing

Advanced Functional Materials, EarlyView.
Develop a LiCl–PEI–PAM hydrogel with 3000% stretchability and excellent optical transparency. Through comparative studies of various salts, confirm that LiCl is the most suitable salt for high TENG output. Achieve excellent freeze‐resistant, dry‐resistant, and rapid self‐healing (10 s) properties even in extreme environments. Balance ionic conductivity,
Hai Anh Thi Le, Thien Trung Luu, Duc‐Manh Dinh, Kyehan Rhee, Kyungwho Choi, Dukhyun Choi, Yong Tae Park   +6 more
wiley   +1 more source

Thermally Pre‐Formed Reconfigurable Resistive Random‐Access Memory Crossbar Arrays: A Dual‐Mode Platform for Robust Physically Unclonable Functions and In‐Memory Computing

Advanced Functional Materials, EarlyView.
A reconfigurable RRAM platform utilizing thermally pre‐formed filaments (TPFs) is developed to realize robust hardware security. By exploiting the thermodynamic stochasticity of TPFs, exceptionally reliable physically unclonable functions (PUFs) are achieved.
Seongbin Kwon, Taewon Lee, Dohyeong Kim, Sungmin Hwang, Sungjoon Kim   +4 more
wiley   +1 more source

M‐ENIAC: A Physics‐Informed Machine Learning Recreation of the First Successful Numerical Weather Forecasts

Geophysical Research Letters
In 1950 the first successful numerical weather forecast was obtained by solving the barotropic vorticity equation using the Electronic Numerical Integrator and Computer (ENIAC), which marked the beginning of the age of numerical weather prediction. Here,
Rüdiger Brecht, Alex Bihlo
doaj   +1 more source

Physics-Informed Graph Neural Networks for Attack Path Prediction

Journal of Cybersecurity and Privacy
The automated identification and evaluation of potential attack paths within infrastructures is a critical aspect of cybersecurity risk assessment. However, existing methods become impractical when applied to complex infrastructures.
Marin François, Pierre-Emmanuel Arduin, Myriam Merad   +2 more
doaj   +1 more source

Sound source directivity interpolation with physics-informed neural networks [PDF]

LAUREA MAGISTRALENel campo della realtà aumentata/virtuale, la riproduzione della direttività delle sorgenti sonore è fondamentale per un’esperienza immersiva di qualità.
Morena, Edoardo
core  

Learning strategies for physics-informed neural networks

Physics-informed neural networks (PINNs) are at the forefront of scientific machine learning, making possible the creation of machine intelligence that is cognizant of physical laws and able to accurately simulate them. This thesis studies the challenges
Wong, Jian Cheng
core   +1 more source