-
novel machine learning models—including Physics-Informed Neural Networks (PINNs), variational autoencoders, and geometric deep learning—to fuse multimodal data from diverse experimental probes like Bragg
-
model classifiers (PLS-DA, random forest, neural network, etc) towards unraveling materials structure-function relationships, and are familiar with optimization approaches such as genetic search, Bayesian
-
structural models and compute electronic and vibrational properties. Develop and train neural-network or other machine-learned interatomic potentials to enable large-scale molecular dynamics (MD) simulations
Searches related to neural network
Enter an email to receive alerts for neural-network positions