danesabo/Obsidian
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

vault backup: 2024-11-06 14:50:08

Browse Source
This commit is contained in:
Dane Sabo 2024-11-06 14:50:08 -05:00
parent e747bc1099
commit 646559ac53
1 changed files with 15 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
201 Metadata/My Library.bib
View File

@ -8632,6 +8632,21 @@ Insights from the Social Sciences.pdf}
file = {/home/danesabo/Zotero/storage/UGGXMX32/Nichol and Dhariwal - 2021 - Improved Denoising Diffusion Probabilistic Models.pdf;/home/danesabo/Zotero/storage/BGVIKW43/2102.html} file = {/home/danesabo/Zotero/storage/UGGXMX32/Nichol and Dhariwal - 2021 - Improved Denoising Diffusion Probabilistic Models.pdf;/home/danesabo/Zotero/storage/BGVIKW43/2102.html}
} }
@online{nicholImprovedDenoisingDiffusion2021a,
title = {Improved {{Denoising Diffusion Probabilistic Models}}},
author = {Nichol, Alex and Dhariwal, Prafulla},
date = {2021-02-18},
eprint = {2102.09672},
eprinttype = {arXiv},
doi = {10.48550/arXiv.2102.09672},
url = {http://arxiv.org/abs/2102.09672},
urldate = {2024-11-06},
abstract = {Denoising diffusion probabilistic models (DDPM) are a class of generative models which have recently been shown to produce excellent samples. We show that with a few simple modifications, DDPMs can also achieve competitive log-likelihoods while maintaining high sample quality. Additionally, we find that learning variances of the reverse diffusion process allows sampling with an order of magnitude fewer forward passes with a negligible difference in sample quality, which is important for the practical deployment of these models. We additionally use precision and recall to compare how well DDPMs and GANs cover the target distribution. Finally, we show that the sample quality and likelihood of these models scale smoothly with model capacity and training compute, making them easily scalable. We release our code at https://github.com/openai/improved-diffusion},
pubstate = {prepublished},
keywords = {Computer Science - Artificial Intelligence,Computer Science - Machine Learning,Statistics - Machine Learning},
file = {/home/danesabo/Zotero/storage/PNYP438A/Nichol and Dhariwal - 2021 - Improved Denoising Diffusion Probabilistic Models.pdf;/home/danesabo/Zotero/storage/V44S65J5/2102.html}
}
@article{nicolCommonWeaknessEnumerations2023, @article{nicolCommonWeaknessEnumerations2023,
title = {Toward {{Common Weakness Enumerations}} in {{Industrial Control Systems}}}, title = {Toward {{Common Weakness Enumerations}} in {{Industrial Control Systems}}},
author = {Nicol, David M. and Shannon, Gregory and Akbar, Monika and Bishop, Matt and Chaney, Michael and Luallen, Matthew}, author = {Nicol, David M. and Shannon, Gregory and Akbar, Monika and Bishop, Matt and Chaney, Michael and Luallen, Matthew},