-
methods with optimization and decision-support models. Background in one or more of the following: time-series analysis, neural networks, forecasting, uncertainty quantification, sensitivity analysis
-
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
Searches related to neural network
Enter an email to receive alerts for neural-network positions