From c20fffc6d89ae3ce14330a0a7762402a8e320719 Mon Sep 17 00:00:00 2001 From: Dane Sabo Date: Fri, 6 Sep 2024 15:18:05 -0400 Subject: [PATCH] vault backup: 2024-09-06 15:18:05 --- 4. Qualifying Exam/2. Writing/1. QE Goals and Outcomes.md | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/4. Qualifying Exam/2. Writing/1. QE Goals and Outcomes.md b/4. Qualifying Exam/2. Writing/1. QE Goals and Outcomes.md index f59ae081..5f64500f 100644 --- a/4. Qualifying Exam/2. Writing/1. QE Goals and Outcomes.md +++ b/4. Qualifying Exam/2. Writing/1. QE Goals and Outcomes.md @@ -5,5 +5,6 @@ 1. Use diffusion generative diffusion models to create examples of perturbed plants 2. You can evaluate robustness of an abstract controller, but actually testing it on real plants is more difficult. 2. What are the outcomes? - 1. Use a generative model to create an unstructured plant perturbations - 2. \ No newline at end of file + 1. Train a diffusion generative model to generate Bode plots of dynamic systems. + 2. Use that generative model to generate perturbations of a given input plant + 3. Modulate the amount of perturbation by modulating the amount of noise used in the diffusion model \ No newline at end of file