Workshop: Uncertainty Management and Machine Learning in Engineering Applications


Date: November 16-17, 2020  
Venue: Virtual event

Workshop Outline

Many high-consequence applications require various levels of risk management to ensure that project objectives are met. In such applications, the accurate quantification and management of risk often depend on large-scale computational models of the underlying physical processes-the outputs of which are plagued with uncertainties. These uncertainties arise from various sources including unverifiable or inaccurate model assumptions, unknown model parameters, estimated parameters using noisy or corrupt data, and underlying stochastic variability. To further complicate matters, the accurate quantification of statistical rare events for risk management typically requires numerous simulations of these models, which is computationally infeasible for many large-scale applications. Consequently, machine learning is likely to play a pivotal role in the risk management of these applications. During this workshop, we will investigate the interplay between machine learning, risk management and large engineering applications with talks from experts in these areas. Our goal is to facilitate conversations and to foster collaborations between experts in these traditionally disparate fields.

List of Speakers, Schedule, Abstracts and Presentations

List of Speakers
Conference Schedule
Abstracts
Presentation Recordings

Organizers

Stan Uryasev, Pawel Polak, and Kevin Maritato Stony Brook University
Drew P. Kouri, Sandia National Laboratories

Contact Information

Mr. Kevin Maritato
kevin.maritato@stonybrook.edu

Prof. Stan Uryasev
Applied Mathematics and Statistics
Stony Brook University
stanislav.uryasev@stonybrook.edu
Cell Phone: (352) 213-3457

Dr. Drew P. Kouri
Optimization & Uncertainty Quantification
Sandia National Laboratories
dpkouri@sandia.gov