Neural Networks to Accelerate Scientific Computing
Development and application of neural networks to accelerate scientific computing in areas of mechanistic simulation, parameter estimation, model selection, and optimization of materials and structures.
Jan 1, 2025
Residual-based error corrector operator to enhance accuracy and reliability of neural operator surrogates of nonlinear variational boundary-value problems
Topology optimization of the diffusivity field in a nonlinear diffusion model. Neural operator and neural operator with corrector employed as a surrogate of the forward model. Comparing the optimizers of the topology optimization problem for different cases (1) true forward model, (2) neural operator surrogate of the forward model, and (3) neural operator with corrector.
Jun 21, 2023
Mutual-Information Based Optimal Experimental Design for Hyperpolarized 13C-Pyruvate MRI
Jun 24, 2022