Active Manifold and Model Order Reduction to Accelerate Multidisciplinary Analysis and Optimization - presented by Prof. Charbel Farhat

Active Manifold and Model Order Reduction to Accelerate Multidisciplinary Analysis and Optimization

Prof. Charbel Farhat

Prof. Charbel Farhat
Slide at 42:10
Charbel Sampling the Parameter Domain for Training: Curse of Dimensionality Uniform sampling at least 2 points in each direction (dimension of the parameter domain D C R N at least 2 N, "samples, independently of the type of surrogate model Number of samples 1 024 32 768 1048576 advantage for PROMs over data regression in general (RSMs, ANNs, GPs, etc.) because a PROM is physics-aware
Share slide
Summary (AI generated)

If you are conducting a data regression, you will need more data than usual. In the case of the runs, the physics can provide some help, but it also highlights the curse of dimensionality.