6 bayesian-inference-"Integreat--Norwegian-Centre-for-Knowledge-driven-Machine-Learning" positions at NIST
-
guiding materials measurement experiments to acclerate learning the synthesis-process-structure-property relationship. Machine learning methods include, but are not limited to, Bayesian inference
-
the collection and analysis of environmental samples from nuclear sites. Collective and individual particulate material from environmental samples can be characterized to infer details of nuclear
-
characterization tools for closed loop experiment design, execution, and analysis, where experiment design is guided by active learning, Bayesian optimization, and similar methods. A key challenge is the integration
-
learning with machine-controlled measurement tools for closed loop experiment design, execution, and analysis, where experiment design is guided by active learning, Bayesian optimization, and similar methods
-
diagnostics of hot plasmas with temperatures in hundreds of thousands or millions degrees is one of the primary and sometimes the only techniques to infer plasma properties. Such hot plasmas can be found in
-
be inferred from initial or final state materials property measurements such as sorbent microstructure, but must be measured in situ during the sorption or release process. This project focuses