File:Comparison of loss functions.png
Size of this preview: 800 × 420 pixels. Other resolutions: 320 × 168 pixels | 640 × 336 pixels | 1,024 × 538 pixels | 1,545 × 811 pixels.
Original file (1,545 × 811 pixels, file size: 41 KB, MIME type: image/png)
|
This is a file from the Wikimedia Commons. The description on its description page there is shown below.
|
Summary
| Description |
English: Smooth Mean Absolute Error (SMEA) loss proposed in https://arxiv.org/abs/2303.09935 outperforms the Squared error, Huber and Log-Cosh losses on datasets with significantly many outliers is proposed. This smooth absolute error loss function is infinitely differentiable and more closely approximates the absolute error loss compared to the Huber and Log-Cosh losses used for robust regression. |
| Date | |
| Source | Own work |
| Author | M.Zkuba |
SMAE loss was proposed by Mathew Mithra Noel (https://orcid.org/0000-0002-3442-1642)
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 | Dimensions | User | Comment | |
|---|---|---|---|---|
| current | 09:35, 9 November 2023 | 1,545 × 811 (41 KB) | M.Zkuba | Uploaded own work with UploadWizard |
File usage
The following page uses this file:
