Sort by
Refine Your Search
-
Listed
-
Field
-
developing new machine learning methodologies that tackle unique computational problems in healthcare applications. We use large real-world complex datasets, including data extracted from electronic health
-
inequalities Markov processes and stochastic analysis Theoretical analysis of neural networks and deep learning Foundations of reinforcement learning and bandit algorithms Mathematical and algorithmic
-
systems (ITS). In particular, the successful candidate will conduct cutting-edge research in: Developing physics-informed neural networks (PINNs) for complex dynamical systems modeling and observer design
-
(e.g., transportation networks, manufacturing systems, and truck routing). Assessing the relevance of the intake fraction (i.e., exposure efficiency) of major emission sources as a critical metric for
-
healthcare applications. We use large real-world complex datasets, including data extracted from electronic health records and medical images, for applications pertaining to patient diagnostics and prognostics
-
to develop novel enabling technology on hydrodynamic stability analysis that has applications in the study of the development of singularities, the long-time behavior of complex systems, the formation
-
workflows in complex organizational settings. Qualifications: Applicants must have a PhD in Computer Science or related field. Experience in one or more ML domains, such as deep learning, reinforcement