News for hackers. Stuff that matters.
Re:Seeking early signals of dementia in driving and credit s... by timy2shoes on Thursday August 26, 2021 @06:09PM (#28321616)
Fantastic point. Another thing about academic ml models is that they're commonly evaluated on in-sample data. For example, medical AI devices are commonly evaluated on data coming from the same source/hospital that the training data comes from (see https://www-cdn.law.stanford.edu/wp-content/uploads/2021/04/...). This leads to over-confidence in the performance because of overfitting of batch effects.

There are no comments on this comment yet.