XinshaoAmosWang/DeepCriticalLearning

Deep Critical Learning. Implementation of ProSelfLC, IMAE, DM, etc.

34
/ 100
Emerging

This project offers robust deep learning methods for practitioners working with noisy or inaccurately labeled datasets. It takes a deep learning model and a dataset, and outputs a more reliable model trained using techniques like Progressive Self Label Correction (ProSelfLC). This helps machine learning engineers and researchers build more accurate models even when data quality is imperfect.

No commits in the last 6 months.

Use this if you are training deep neural networks and suspect your dataset contains mislabeled examples or noise that is hindering your model's performance.

Not ideal if your datasets are perfectly clean and accurately labeled, or if you are not working with deep learning models.

machine-learning deep-learning data-quality model-robustness protein-classification
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

31

Forks

4

Language

Python

License

Last pushed

Dec 23, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/XinshaoAmosWang/DeepCriticalLearning"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.