Relative stability toward diffeomorphisms indicates performance in deep nets
| Main Authors: | Leonardo Petrini, Alessandro Favero, Mario Geiger, Matthieu Wyart |
|---|---|
| Format: | Proceeding Journal |
| Bahasa: | eng |
| Terbitan: |
, 2021
|
| Subjects: | |
| Online Access: |
https://zenodo.org/record/5589870 |
| ctrlnum |
5589870 |
|---|---|
| fullrecord |
<?xml version="1.0"?>
<dc schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd"><creator>Leonardo Petrini</creator><creator>Alessandro Favero</creator><creator>Mario Geiger</creator><creator>Matthieu Wyart</creator><date>2021-10-21</date><description>Code and pre-trained models used for the paper Relative stability toward diffeomorphisms indicates performance in deep nets, Petrini L. et al., NeurIPS2021.
Fifteen different network architectures have been pre-trained on 4 benchmark datasets of images (MNIST, FashionMNIST, CIFAR10, SVHN) for different initialization seeds and train-set sizes for a total of 2'000+ pretrained models.
Details on the available models can be found in the Pandas dataframe: pretrained_models_dataframe.pkl
More details about the trainings are available in the reference paper (Appendix E) and at the GitHub repository: https://github.com/leonardopetrini/diffeo-sota
For more info contact leonardo.petrini at epfl.ch</description><identifier>https://zenodo.org/record/5589870</identifier><identifier>10.5281/zenodo.5589870</identifier><identifier>oai:zenodo.org:5589870</identifier><language>eng</language><relation>arxiv:arXiv:2105.02468</relation><relation>doi:10.5281/zenodo.5589869</relation><rights>info:eu-repo/semantics/openAccess</rights><rights>https://creativecommons.org/licenses/by/4.0/legalcode</rights><subject>deep learning</subject><subject>cifar10</subject><subject>mnist</subject><subject>pretrained</subject><subject>image classification</subject><subject>resnet</subject><subject>vgg</subject><subject>alexnet</subject><subject>fashionmnist</subject><subject>svhn</subject><title>Relative stability toward diffeomorphisms indicates performance in deep nets</title><type>Journal:Proceeding</type><type>Journal:Proceeding</type><recordID>5589870</recordID></dc>
|
| language |
eng |
| format |
Journal:Proceeding Journal Journal:Journal |
| author |
Leonardo Petrini Alessandro Favero Mario Geiger Matthieu Wyart |
| title |
Relative stability toward diffeomorphisms indicates performance in deep nets |
| publishDate |
2021 |
| topic |
deep learning cifar10 mnist pretrained image classification resnet vgg alexnet fashionmnist svhn |
| url |
https://zenodo.org/record/5589870 |
| contents |
Code and pre-trained models used for the paper Relative stability toward diffeomorphisms indicates performance in deep nets, Petrini L. et al., NeurIPS2021.
Fifteen different network architectures have been pre-trained on 4 benchmark datasets of images (MNIST, FashionMNIST, CIFAR10, SVHN) for different initialization seeds and train-set sizes for a total of 2'000+ pretrained models.
Details on the available models can be found in the Pandas dataframe: pretrained_models_dataframe.pkl
More details about the trainings are available in the reference paper (Appendix E) and at the GitHub repository: https://github.com/leonardopetrini/diffeo-sota
For more info contact leonardo.petrini at epfl.ch |
| id |
IOS16997.5589870 |
| institution |
ZAIN Publications |
| institution_id |
7213 |
| institution_type |
library:special library |
| library |
Cognizance Journal of Multidisciplinary Studies |
| library_id |
5267 |
| collection |
Cognizance Journal of Multidisciplinary Studies |
| repository_id |
16997 |
| subject_area |
Multidisciplinary |
| city |
Stockholm |
| province |
INTERNASIONAL |
| shared_to_ipusnas_str |
1 |
| repoId |
IOS16997 |
| first_indexed |
2022-06-06T04:38:17Z |
| last_indexed |
2022-06-06T04:38:17Z |
| recordtype |
dc |
| _version_ |
1734902697035825152 |
| score |
17.538404 |