News for hackers. Stuff that matters.
Re:A better way to build ML: Why you should be using Active ... by razcle on Thursday February 04, 2021 @01:10PM (#26028081)
I'd also point out that people always focus on just the labelling savings from active learning but there are other benefits in practice too: 1) faster feedback on model performance during the annotation process and 2) Better engagement from the annotators as they can see the benefit of their work.
Re:A better way to build ML: Why you should be using Active ... by andy99 on Thursday February 04, 2021 @03:08PM (#26029209)
I'd add that there is a deep connection between active learning and understanding the "domain of expertise" of a model, for example what inputs are ambiguous or low confidence, and which are out of distribution. E.g. BALD is a form of out of distribution detection - a point with high disagreement it not only useful to add to the training pool, it is a point for which the current model has no business making a prediction.