4 papers
Beyond Compression: Training Latent Representations for Stable Long-Horizon Rollout in Neural Surrogate Solvers
Andreas E. Robertson, Ashley T. Lenau, John D. Shimanek +5
Latent neural surrogate solvers, or latent dynamics models, accelerate simulations of time-dependent physical systems by evolving a compressed latent space rather than resolving fu…
Microstructure-based Variational Neural Networks for Robust Uncertainty Quantification in Materials Digital Twins
Andreas E. Robertson, Samuel B. Inman, Ashley T. Lenau +4
Aleatoric uncertainties - irremovable variability in microstructure morphology, constituent behavior, and processing conditions - pose a major challenge to developing uncertainty-r…
Training Variation of Physically-Informed Deep Learning Models
Ashley Lenau, Dennis Dimiduk, Stephen R. Niezgoda
A successful deep learning network is highly dependent not only on the training dataset, but the training algorithm used to condition the network for a given task. The loss functio…
Importance of hyper-parameter optimization during training of physics-informed deep learning networks
Ashley Lenau, Dennis M. Dimiduk, Stephen R. Niezgoda
Incorporating scientific knowledge into deep learning (DL) models for materials-based simulations can constrain the network's predictions to be within the boundaries of the materia…