Opportunity at National Institute of Standards and Technology NIST
Uncertainty Analysis for Machine Learning and Optimization Applications
Material Measurement Laboratory, Chemical Sciences Division
Please note: This Agency only participates in the February and August reviews.
|David Allan Sheen
Computational tools for analysis and model development have been widely used in many applications, but the predictions of these models are not complete without an estimate of the uncertainty in those predictions. With uncertainty analysis, the model predictions are made more robust and reliable. This project seeks to understand and develop techniques for uncertainty analysis in machine learning and advanced optimization for fields including precision medicine, biomanufacturing, omics research, and kinetic model development. Techniques for uncertainty estimation will range from non-parametric methods such as bootstrapping to fully Bayesian analysis.
W. F. C. Rocha, D. A. Sheen, SAR and QSAR in Environmental Research (2016), 799-811.
D. A. Sheen, W. F. C. Rocha, K. A. Lippa, D. W. Bearden, Chemometrics and Intelligent Laboratory Systems 162 (2017), 10-20.
Machine learning; Outlier detection; Optimization; Informatics; Chemometrics; Metabolomics; Bayesian analysis; Uncertainty analysis; Uncertainty quantification
Open to U.S. citizens
Open to Postdoctoral applicants