https://github.com/lilianweng/generalization-experiment
TBA
https://github.com/lilianweng/generalization-experiment
Last synced: 6 months ago
JSON representation
TBA
- Host: GitHub
- URL: https://github.com/lilianweng/generalization-experiment
- Owner: lilianweng
- Created: 2019-03-14T21:26:57.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2019-03-22T07:00:04.000Z (over 6 years ago)
- Last Synced: 2025-03-30T03:11:10.485Z (6 months ago)
- Language: Python
- Size: 464 KB
- Stars: 75
- Watchers: 2
- Forks: 3
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# generalization-experiment
There are three experiments involved:
1. Modern risk curve for DL: `risk_curve.py` and `risk_curve_evaluate_model.py`
2. Measure intrinsic dimensions: `intrinsic_dimensions.py` and `intrinsic_dimensions_measurement.py`
3. Measure re-initialization and re-randomization robustness of layers: `layer_equality.py`
See blog post ["Are Deep Neural Networks Dramatically Overfitted?"](http://lilianweng.github.io/lil-log/2019/03/14/are-deep-neural-networks-dramatically-overfitted.html) for more details.