Neural Collapse Animation
Abstract/Contents
- Abstract
- This figure demostrate via animation the phenomenon called Neural Collapse described in the paper "Prevalence of Neural Collapse during the terminal phase of deep learning training" by Papyan, Han, and Donoho in PNAS.
Description
| Type of resource | moving image |
|---|---|
| Date created | 2020 |
Creators/Contributors
| Author | Papyan, Vardan |
|---|---|
| Author | Han, Xiaoyan (X.Y.) |
| Author | Donoho, David L. |
Subjects
| Subject | Statistics Department |
|---|---|
| Subject | Stanford School of Arts and Sciences |
| Subject | Machine learning |
| Subject | Deep learning |
| Subject | Adversarial robustness |
| Subject | Simplex Equiangular Tight Frame |
| Subject | Nearest Class Center |
| Subject | Inductive bias |
| Genre | Motion picture |
Bibliographic information
| Related Publication | Papyan, Vardan and Han, X. Y. and Donoho, David L. (2020). "Prevalence of Neural Collapse during the terminal phase of deep learning training." PNAS. https://doi.org/10.1073/pnas.2015509117 |
|---|---|
| Location | https://purl.stanford.edu/br193mh4244 |
Access conditions
- Use and reproduction
- User agrees that, where applicable, content will not be used to identify or to otherwise infringe the privacy or confidentiality rights of individuals. Content distributed via the Stanford Digital Repository may be subject to additional license and use restrictions applied by the depositor.
- License
- This work is licensed under a Creative Commons Attribution Non Commercial No Derivatives 3.0 Unported license (CC BY-NC-ND).
Collection
Stanford Research Data
View other items in this collection in SearchWorksContact information
- Contact
- xiaoyanh@stanford.edu
Also listed in
Loading usage metrics...