IN
United States
Purdue University - Department of Mathematics
L2 approximation, operator learning, machine learning, data-driven scientific computing
Three-dimensional Avatar Reconstruction, Gaussian Splatting, Pixel-wise Segmentation, Aritificial Intelligence, Metaverse
Machine learning, Bayesian inference, Data-driven discovery, Bayesian group Lasso regression, Bayesian model selection, Bayesian sparse learning
replica exchange, Bayesian physics-informed neural network, Markov Chain Monte Carlo, Machine Learning, Deep learning, Neural network
Reduced-order Model (ROM), Data assimilation, Uncertainty quantification, ensemble kalman filter, Sparse Observations.
Kolmogorov-Arnold Networks (KANs), Scalar Auxiliary Variable (SAV) method, Evolutionary Neural Network, Partial Differential Equations
Operator learning, Evolutionary neural networks, Energy Dissipative, Parametric equation, Scalar auxiliary variable, Deep Learning
Physics Informed Neural Networks, Non-dominated Sorting Genetic Algorithm III, Kalman Filter, Missing Physics, Inverse Problem
Operator Learning, Evolutionary Neural Networks, Energy Dissipative, parametric equation, scalar auxiliary variable, Deep learning
Replica exchange Monte Carlo, Langevin diffusion, preconditioned Crank-Nicolson scheme, Bayesian inverse problem
partial differential equations, operator learning, DeepONet, uncertainty quantification, out-of-distribution, active learning
Sparse Identification, Nonlinear Dynamical Systems, Laplace Transform, Model Identification, Model Evaluation
Deep operator learning, distributed training, pretraining, fine-tuning, low-rank adaptation (LoRA), physics-informed learning
Machine learning, Physics-informed neural networks, Nonlinear DEs, Multiple solutions, Homotopy continuation method
Turbulence modeling, deconvolution, Riemannian Optimization, Quotient manifold, Large eddy simulations, Divergence-free wavelets
Operator Learning, Laplace Neural Operators, Multi Fidelity, Uncertainty Quantification, Langevin Dynamics, Replica Exchange
Voltage Stability, Conformalized Prediction, Deep Operator Networks, Fine-tuning, Uncertainty Quantification, Power Grid Dynamics
Kolmogorov-Arnold Networks (KANs), Conformal Prediction, Uncertainty Quantification, Scientific Machine Learning, Multi-Fidelity Modeling, Ensemble Learning
Profiled Rib, Internal Cooling Channels, Gas Turbine, Heat transfer, Deep Operator Networks, Bayesian MCMC, Optimization
Physical law discovery, Uncertainty quantification, Active learning, Bayesian method, Markov Chain Monte Carlo Langevin dynamics
Shape optimization, Generative Prior, Electrical Impedance Tomography
Radiation transfer, M1 method, Moment closure, Deep learning, 12 Discontinuous Galerkin method, Hyperbolicity
Physics-informed Operator Learning, Evolutionary Multi-Objective Optimization, Uncertainty Quantification, Replica Exchange Stochastic Gradient Langevin Dynamics, Parametric PDEs, Inverse Problem
Low-rank adaptationEvolutionary deep neural networkpartial differential equationScientific machine learningComputational efficiency
Deep learning, Partial differential equations, Boundary condition, Kolmogorov-Arnold networks, Evolutionary neural networks
Deep Learning, Partial differential equations, Boundary condition, Kolmogorov-Arnold Networks, Evolutionary Neural Networks, radial basis functions
Turbulence modeling, deconvolution, Riemannian optimization, Quotient manifold, Large eddy simulations, Divergence-free wavelets
Physics Informed Neural Network (PINN), Deep Operator Network (DeepONet), Kolmogorov-Arnold Networks (KANs), Rational activation functions, Partial differential equations
Scientific Machine Learning, Deep learning, Partial differential equations, Tangent-Space projection, Kolmogorov-Arnold networks, Evolutionary networks
Scientific Machine Learning, Deep learning, Partial Differential Equations, Weak formulation, Kolmogorov-Arnold networks, Evolutionary networks
POD-DeepONet, Photonic Crystals, Band Structure Modeling, Bloch Eigenvalue Problems, Inverse Design
reduced basis methods, operator learning, DeepONet, Finite element methods, Parametric PDEs
Scientific Machine Learning, Physics-Informed Neural Networks, Neural Operators, Spectral Optimization, Scalar Auxiliary Variable, Parametric PDEs
