Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Allingham, James U."'
Farquhar et al. [2021] show that correcting for active learning bias with underparameterised models leads to improved downstream performance. For overparameterised models such as NNs, however, correction leads either to decreased or unchanged perform
Externí odkaz:
http://arxiv.org/abs/2112.06926
In active learning, the size and complexity of the training dataset changes over time. Simple models that are well specified by the amount of data available at the start of active learning might suffer from bias as more points are actively sampled. F
Externí odkaz:
http://arxiv.org/abs/2112.06796