Deep learning has triggered the current rise of artificial intelligence and is the workhorse of
today's machine intelligence. Numerous success stories have rapidly spread all over …

Artificial vision has often been described as one of the key remaining challenges to be
solved before machines can act intelligently. Recent developments in a branch of machine …

Neural network classifiers can largely rely on simple spurious features, such as
backgrounds, to make predictions. However, even in these cases, we show that they still …

Deep classifiers are known to rely on spurious features—patterns which are correlated with
the target on the training data but not inherently relevant to the learning problem, such as the …

Deep neural networks (DNNs) have had extraordinary successes in classifying
photographic images of objects and are often described as the best models of biological …

Distribution shifts—where the training distribution differs from the test distribution—can
substantially degrade the accuracy of machine learning (ML) systems deployed in the wild …

We assess the tendency of state-of-the-art object recognition models to depend on signals
from image backgrounds. We create a toolkit for disentangling foreground and background …

Deep learning has already achieved remarkable results in many fields. Now it's making
waves throughout the sciences broadly and the life sciences in particular. This practical …

We identify and formalize a fundamental gradient descent phenomenon resulting in a
learning proclivity in over-parameterized neural networks. Gradient Starvation arises when …

Abstract Convolutional Neural Networks (CNNs) are commonly assumed to be invariant to
small image transformations: either because of the convolutional architecture or because …