-
data-model integration, leveraging the U.S. Department of Energy’s (DOE) Leadership-Class Computing Facilities to advance predictive understanding of complex environmental systems. Major Duties
-
/models which accurately capture the complexities of the data, with robust estimates of confidence in predictions and compressed quantities of interest on defined domains; Fast and scalable algorithms
-
focus on designing architectures and models that effectively capture the complexities of data, provide robust confidence estimates in predictions, and generate compressed quantities of interest tailored
-
understanding and models for relations among simulation parameters, AI models, and predictive performance. As a UT-ORII fellow, your career will develop in collaboration with researchers from both UT and ORNL
-
photosynthesis to join the new pilot study of Generative Pretrained Transformer for genomic photosynthesis (GPTgp). The GPTgp project aims to develop a foundational holistic model of photosynthesis that will scale