File:Double descent.png
Jump to navigation
Jump to search
Size of this preview: 800 × 400 pixels. Other resolutions: 320 × 160 pixels | 640 × 320 pixels | 1,094 × 547 pixels.
Original file (1,094 × 547 pixels, file size: 186 KB, MIME type: image/png)
Summary
| Description |
English: Double descent: modern overparametrized models achieve low generalization error despite being able to interpolate the data. Adapted from Belkin (2021) "Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation." |
| Date | |
| Source | Own work |
| Author | Dkarkada |
Licensing
I, the copyright holder of this work, hereby publish it under the following license:
This file is licensed under the Creative Commons Attribution-Share Alike 4.0 International license.
- You are free:
- to share – to copy, distribute and transmit the work
- to remix – to adapt the work
- Under the following conditions:
- attribution – You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- share alike – If you remix, transform, or build upon the material, you must distribute your contributions under the same or compatible license as the original.
File history
Click on a date/time to view the file as it appeared at that time.
| Date/Time | Thumbnail | Dimensions | User | Comment | |
|---|---|---|---|---|---|
| current | 17:55, 8 May 2023 | | 1,094 × 547 (186 KB) | wikimediacommons>Dkarkada | changed xaxis label |
File usage
The following page uses this file:
