PrototypeCommon
google/TrustScore
To Trust Or Not To Trust A Classifier. A measure of uncertainty for any trained (possibly black-box) classifier which is more effective than the classifier's own implied confidence (e.g. softmax probability for a neural network).
Archived: this repository is read-only
- Owner
- google (organization)
- Stars
- Stars: 181
- Forks
- Forks: 41
- Language
- Jupyter Notebook
- License
- Apache-2.0
- Created
- 2018
- Topics
- uncertainty-neural-networksuncertainty-estimation
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by google
All 1,050 repos by google- google/material-design-iconsStars: 54,214LTS
- google/guavaStars: 51,915JavaLTS
- google/zxStars: 45,832JavaScriptLTS
- google/styleguideStars: 39,788Emacs LispLTS
- google/googletestStars: 39,690C++LTS
- google/leveldbStars: 39,516C++LTS
Nearby in Jupyter Notebook
All Jupyter Notebook repos- pollen-robotics/PincOpenStars: 181Jupyter NotebookPrototype
- safety-research/assistant-axisStars: 181Jupyter NotebookPrototype
- jexp/neo4jevStars: 181Jupyter NotebookPrototype
- yoavram/CS1001.pyStars: 181Jupyter NotebookPrototype
- ricardoduarte/python-for-developersStars: 181Jupyter NotebookPrototype
- jrjohansson/numerical-python-book-codeStars: 181Jupyter NotebookPrototype