Re:Deep learning outperformed dermatologists in melanoma ima...
by ppod on Tuesday April 30, 2019 @01:56PM
(#19790289)
> test data should be balanced or they should correct for this in the analysis.
Why should it be balanced? It should be the expected natural clinical class distribution, no? The humans have priors about this too. If anything, it should be more imbalanced, as I would guess (I would hope!) that less than 20% of scans are malignant.
Why should it be balanced? It should be the expected natural clinical class distribution, no? The humans have priors about this too. If anything, it should be more imbalanced, as I would guess (I would hope!) that less than 20% of scans are malignant.