From 062c5c2ed49eb88d05efcd3757518c25612290c3 Mon Sep 17 00:00:00 2001 From: Dane Sabo Date: Mon, 28 Oct 2024 08:59:10 -0400 Subject: [PATCH] vault backup: 2024-10-28 08:59:10 --- .../2 Writing/3. QE Research Approach.md | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/4 Qualifying Exam/2 Writing/3. QE Research Approach.md b/4 Qualifying Exam/2 Writing/3. QE Research Approach.md index e3b20b6f..3d8d8143 100644 --- a/4 Qualifying Exam/2 Writing/3. QE Research Approach.md +++ b/4 Qualifying Exam/2 Writing/3. QE Research Approach.md @@ -24,4 +24,13 @@ Something to justify, why diffusion model as opposed to other generative AI 1. Generating unstructured perturbations is pretty hard 2. They need to be 'random' 3. diffusion model is good at creating novel examples (cite!) -4. \ No newline at end of file +4. we can use diffusion models to solve this problem of generating examples +5. But how does a diffusion model work? +6. Diffusion model uses two processes +7. a forward process that introduces noise into an 'input' +8. this forward process does this using several small steps of noise +9. This noise is a gaussian noise +10. over time this forward process degrades the input until it is unrecognizable +11. This takes several several iterations, but is dependent on the amount of noise in each step +12. +13. A reverse process that tries to remove the noise \ No newline at end of file