Published July 12, 2023
| Version v0.1.1rc4
Software
Open
mit-ll-responsible-ai/equine: v0.1.1rc4
- 1. MIT Lincoln Laboratory
Description
EQUI(NE)^2 (equine): Establishing Quantified Uncertainty for Neural Networks
The goal of this package is to make it simple to add modern uncertainty quantification (UQ) techniques to existing PyTorch models to produce label predictions with calibrated probabilities and out-of-distribution indicators.
Files
mit-ll-responsible-ai/equine-v0.1.1rc4.zip
Files
(973.0 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:7d7c0333528dd5af9e842672d5ce4977
|
973.0 kB | Preview Download |
Additional details
Related works
- Is supplement to
- https://github.com/mit-ll-responsible-ai/equine/tree/v0.1.1rc4 (URL)