We consider the problem of training a classification model with group annotated training
data. Recent work has established that, if there is distribution shift across different groups …

Which parts of a dataset will a given model find difficult? Recent work has shown that SGD-
trained models have a bias towards simplicity, leading them to prioritize learning a majority …

Background Machine learning (ML) approaches are a crucial component of modern data
analysis in many fields, including epidemiology and medicine. Nonlinear ML methods often …

Neural networks (NNs) are known to exhibit simplicity bias where they tend to prefer
learning'simple'features over more'complex'ones, even when the latter may be more …

Traditional deep learning algorithms often fail to generalize when they are tested outside of
the domain of the training data. The issue can be mitigated by using unlabeled data from the …

On several key issues we agree with the commentators. Perhaps most importantly, everyone
seems to agree that psychology has an important role to play in building better models of …

Deep learning models have been found with a tendency of relying on shortcuts, ie, decision
rules that perform well on standard benchmarks but fail when transferred to more …

Background It has been shown that AI models can learn race on medical images, leading to
algorithmic bias. Our aim in this study was to enhance the fairness of medical image models …

Deep convolutional neural networks for dense prediction tasks are commonly optimized
using synthetic data, as generating pixel-wise annotations for real-world data is laborious …

Deep learning systems frequently fail at out-of-context (OOC) prediction, the problem of
making reliable predictions on uncommon or unusual inputs or subgroups of the training …