Event Calendar
Prev MonthPrev Month Next MonthNext Month
USACM UQ Virtual Seminar
Wednesday, December 08, 2021, 2:00 PM - 3:00 PM CST
Category: Events

USACM UQ Virtual Seminar

Bayesian Learning of Neural Networks for Small or Imbalanced Data Sets


Audrey Olivier, University of Southern California


Lori Graham-Brady, Johns Hopkins University



Data-based predictive models such as neural networks are showing great potential to be used in various scientific and engineering fields. They can be used in conjunction with physics-based models to account for missing or hard-to-model physics, or as surrogates to replace high-fidelity, overly costly physics-based simulations. However, in many engineering fields data is expensive to obtain and data scarcity and / or data imbalance is a challenge. Many physical processes are also random in nature and exhibit large aleatory uncertainties. Bayesian methods allow for a comprehensive account of both aleatory and epistemic uncertainties; however, they are challenging to use for overly parameterized problems such as neural networks. This talk will present methods based on variational inference and model averaging for probabilistic training of neural networks. An application in surrogate materials modeling will be presented, where data is scarce as it is obtained from expensive high-fidelity materials simulations. Finally, we will show how this probabilistic approach allows to integrate scientific intuitions by defining a meaningful prior and likelihood for training. The example presented pertains to the prediction of ambulance travel time, using real data provided by the New York City Fire Department.