deargen/MT-ENet

Repository for "Improving evidential deep learning via multi-task learning," published in AAAI2022

30
/ 100
Emerging

This project offers a refined way to build machine learning models that not only predict numerical outcomes but also estimate how confident they are in those predictions. It takes in existing evidential regression networks and outputs a more accurate model with robust uncertainty quantification. This tool is for machine learning researchers and practitioners who need reliable predictions along with a measure of their trustworthiness.

No commits in the last 6 months.

Use this if you need to develop regression models that provide both precise numerical predictions and reliable estimates of their uncertainty, especially in critical applications.

Not ideal if you only need point predictions without any measure of confidence or if you are not working with evidential deep learning frameworks.

predictive-modeling uncertainty-quantification machine-learning-research drug-discovery model-reliability
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

20

Forks

2

Language

Python

License

MIT

Last pushed

Mar 04, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/deargen/MT-ENet"

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