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).

语言：Jupyter Notebook · GitHub 星标：181 · Fork：41

话题：uncertainty-estimation · uncertainty-neural-networks

在 GitHub 上查看原仓库