Results 1 to 10 of about 2,220,071 (341)
RANG: A Residual-based Adaptive Node Generation Method for Physics-Informed Neural Networks [PDF]
arXiv.org, 2022 Learning solutions of partial differential equations (PDEs) with Physics-Informed Neural Networks (PINNs) is an attractive alternative approach to traditional solvers due to its flexibility and ease of incorporating observed data.
Wei Peng +4 more
openalex +3 more sources
MBD-NODE: Physics-informed data-driven modeling and simulation of constrained multibody systems [PDF]
Multibody system dynamicsWe describe a framework that can integrate prior physical information, e.g., the presence of kinematic constraints, to support data-driven simulation in multibody dynamics. Unlike other approaches, e.g., Fully Connected Neural Network (FCNN) or Recurrent
Jingquan Wang +4 more
semanticscholar +3 more sources
IEEE Journal of the Electron Devices Society, 2018 We present a comprehensive theoretical investigation of the quantum confinement limited mobility in the Si1-xGex-channel gate-all-around nanosheet field effect transistor for 5-nm node.
Jiaxin Yao +10 more
doaj +2 more sources
Node and edge nonlinear eigenvector centrality for hypergraphs [PDF]
Communications Physics, 2021 Network scientists have shown that there is great value in studying pairwise interactions between components in a system. From a linear algebra point of view, this involves defining and evaluating functions of the associated adjacency matrix. Recent work
Francesco Tudisco, D. Higham
semanticscholar +1 more source
Network Representation Learning: From Preprocessing, Feature Extraction to Node Embedding [PDF]
ACM Computing Surveys, 2021 Network representation learning (NRL) advances the conventional graph mining of social networks, knowledge graphs, and complex biomedical and physics information networks. Dozens of NRL algorithms have been reported in the literature.
Jingya Zhou +3 more
semanticscholar +1 more source
Nature Electronics, 2023 Quantum-inspired computing systems can be used to efficiently solve combinatorial optimization problems. In developing such systems, a key challenge is the creation of large hardware topologies with all-to-all node connectivity that allow arbitrary ...
H. Lo +4 more
semanticscholar +1 more source
Unifying over-smoothing and over-squashing in graph neural networks: A physics informed approach and beyond [PDF]
arXiv.org, 2023 Graph Neural Networks (GNNs) have emerged as one of the leading approaches for machine learning on graph-structured data. Despite their great success, critical computational challenges such as over-smoothing, over-squashing, and limited expressive power ...
Zhiqi Shao +5 more
semanticscholar +1 more source
Topological quadratic-node semimetal in a photonic microring lattice
Nature Communications, 2023 Graphene, with its two linearly dispersing Dirac points with opposite windings, is the minimal topological nodal configuration in the hexagonal Brillouin zone. Topological semimetals with higher-order nodes beyond the Dirac points have recently attracted
Zihe Gao +7 more
semanticscholar +1 more source
Fractal and Fractional, 2023 In this research work, we investigate the complex structure of soliton in the Fractional Kudryashov–Sinelshchikov Equation (FKSE) using conformable fractional derivatives.
Rashid Ali +5 more
doaj +1 more source
Ideal Photonic Weyl Nodes Stabilized by Screw Rotation Symmetry in Space Group 19
Crystals, 2020 Topological photonics have developed in recent years since the seminal discoveries of topological insulators in condensed matter physics for electrons.
Wenlong Gao, Yao-Ting Wang
doaj +1 more source