Co-Validation: Using Model Disagreement on Unlabeled Data to Validate Classification Algorithms

Madani, Omid, Pennock, David M., Flake, Gary W.

Neural Information Processing Systems 

In the context of binary Classification, we define disagreement as a measure of how often two independently-trained models differ in their Classification of unlabeled data.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found