Residual-based attention in physics-informed neural networks
SJ Anagnostopoulos, JD Toscano… - Computer Methods in …, 2024 - Elsevier
Driven by the need for more efficient and seamless integration of physical models and data,
physics-informed neural networks (PINNs) have seen a surge of interest in recent years …
physics-informed neural networks (PINNs) have seen a surge of interest in recent years …
Inferring turbulent velocity and temperature fields and their statistics from Lagrangian velocity measurements using physics-informed Kolmogorov-Arnold Networks
We propose the Artificial Intelligence Velocimetry-Thermometry (AIVT) method to infer
hidden temperature fields from experimental turbulent velocity data. This physics-informed …
hidden temperature fields from experimental turbulent velocity data. This physics-informed …
Deep neural operators can predict the real-time response of floating offshore structures under irregular waves
The utilization of neural operators in a digital twin model of an offshore floating structure
holds the potential for a significant shift in the prediction of structural responses and health …
holds the potential for a significant shift in the prediction of structural responses and health …
Neuroscience inspired neural operator for partial differential equations
S Garg, S Chakraborty - Journal of Computational Physics, 2024 - Elsevier
We propose, in this paper, a Variable Spiking Wavelet Neural Operator (VS-WNO), which
aims to bridge the gap between theoretical and practical implementation of Artificial …
aims to bridge the gap between theoretical and practical implementation of Artificial …
Inferring in vivo murine cerebrospinal fluid flow using artificial intelligence velocimetry with moving boundaries and uncertainty quantification
JD Toscano, C Wu, A Ladrón-de-Guevara… - Interface …, 2024 - royalsocietypublishing.org
Cerebrospinal fluid (CSF) flow is crucial for clearing metabolic waste from the brain, a
process whose dysregulation is linked to neurodegenerative diseases like Alzheimer's …
process whose dysregulation is linked to neurodegenerative diseases like Alzheimer's …
Learning in PINNs: Phase transition, total diffusion, and generalization
SJ Anagnostopoulos, JD Toscano… - arXiv preprint arXiv …, 2024 - arxiv.org
We investigate the learning dynamics of fully-connected neural networks through the lens of
gradient signal-to-noise ratio (SNR), examining the behavior of first-order optimizers like …
gradient signal-to-noise ratio (SNR), examining the behavior of first-order optimizers like …
Randomized Forward Mode Gradient for Spiking Neural Networks in Scientific Machine Learning
R Wan, Q Zhang, GE Karniadakis - arXiv preprint arXiv:2411.07057, 2024 - arxiv.org
Spiking neural networks (SNNs) represent a promising approach in machine learning,
combining the hierarchical learning capabilities of deep neural networks with the energy …
combining the hierarchical learning capabilities of deep neural networks with the energy …
Hybrid variable spiking graph neural networks for energy-efficient scientific machine learning
Graph-based representations for samples of computational mechanics-related datasets can
prove instrumental when dealing with problems like irregular domains or molecular …
prove instrumental when dealing with problems like irregular domains or molecular …
Neuroscience inspired scientific machine learning (Part-2): Variable spiking wavelet neural operator
S Garg, S Chakraborty - arXiv preprint arXiv:2311.14710, 2023 - arxiv.org
We propose, in this paper, a Variable Spiking Wavelet Neural Operator (VS-WNO), which
aims to bridge the gap between theoretical and practical implementation of Artificial …
aims to bridge the gap between theoretical and practical implementation of Artificial …
Operator Learning for Reconstructing Flow Fields from Sparse Measurements: an Energy Transformer Approach
Abstract Machine learning methods have shown great success in various scientific areas,
including fluid mechanics. However, reconstruction problems, where full velocity fields must …
including fluid mechanics. However, reconstruction problems, where full velocity fields must …