Webinars

SmartUQ’s Best in Class Gaussian Process Models for Simulations

On Demand
Register
Presented by Gavin Jones, Principal Application Engineer
Gavin Jones, Principal Application Engineer, is responsible for performing simulation and statistical work for clients in the automotive, aerospace, defense, gas turbine, and other industries. He is a member of the SAE Chassis Committee as well as a member of AIAA’s Digital Engineering Integration Committee. Gavin is also a key contributor in SmartUQ’s Digital Twin/Digital Thread initiative.

SmartUQ is a powerful Machine Learning (ML) software tool optimally designed for engineering applications such as simulations and digital twins. It was invented to solve modern ML problems across multiple industries including aerospace, automotive, heavy machinery, semiconductor, environmental, natural gas, and others. SmartUQ can be used for handling problems whether large or small, complex or simple.

For ML models such as Gaussian process models, also called Kriging models, training speed and prediction accuracy are of vital importance. Without speed training a model can become infeasible as the scale and complexity of the problem increases. Without high accuracy a ML model’s predictions will have too much uncertainty to be usable. Worse, poor predictive accuracy can lead to decisions being made based on inaccurate information. This can result in catastrophic consequences.

SmartUQ addresses both the need for speed and accuracy with its best in class Gaussian process (GP) models. SmartUQ and many of its customers have performed several benchmarks against other tools, showing that the performance of our GP models is drastically superior to the competition in terms of accuracy, training speed, flexibility and scalability.

Join us for this free webinar in which SmartUQ principal application engineer, Gavin Jones, will introduce SmartUQ’s GP models and present more detailed results of the benchmarks. If interested in a trial version of SmartUQ to see for yourself, please contact [email protected].