FREE WEBINAR Sept. 8: From Optimization to Uncertainty Quantification through Machine Learning

DATE: September 08, 2022
TIME: 03:00 PM EDT/ Noon PDT

In the last decade, advances in machine learning (ML) have led to the ability to build highly accurate predictive models. These predictive models play a key role in Uncertainty Quantification (UQ) as many of the techniques that make up UQ can be too computationally expensive to implement directly; therefore, the training of a much cheaper-to-evaluate predictive model is required in practice.

Using predictive modeling and ideas from UQ, scientists, engineers, and data scientists familiar with optimization can get more value out of their simulations and achieve faster and more reliable optimization results. With this method, you can

• Speed up design optimizations using predictive modeling in place of full fidelity simulation runs;
• Speed up the process of ML model hyperparameter optimization;
• Perform stochastic optimization to account for uncertainty in some model inputs (e.g. simulation boundary conditions, material property parameters, and loading conditions).

This webinar will introduce you to UQ and predictive modeling and the benefits to optimization. Concrete examples will be used for illustration throughout.

You can register here.

Speakers:

Gavin Jones
Principal Application Engineer
SmartUQ

Moderator: Kenneth Wong
Senior Editor
Digital Engineering