Deep neural network models of sensory systems are often proposed to learn
representational transformations with invariances like those in the brain. To reveal these …

Deep neural networks have been embraced as models of sensory systems, instantiating
representational transformations that appear to resemble those in the visual and auditory …

Discovering and exploiting shared, invariant neural activity in electroencephalogram (EEG)
based classification tasks is of significant interest for generalizability of decoding models …

Deep neural networks (DNNs) have demonstrated impressive performance on a wide array
of tasks, but they are usually considered opaque since internal structure and learned …

Abstract Machine learning models are vulnerable to adversarial examples: small changes to
images can cause computer vision models to make mistakes such as identifying a school …

Distinct scientific theories can make similar predictions. To adjudicate between theories, we
must design experiments for which the theories make distinct predictions. Here we consider …

An important goal in deep learning is to learn versatile, high-level feature representations of
input data. However, standard networks' representations seem to possess shortcomings …

Neural networks are vulnerable to input perturbations such as additive noise and
adversarial attacks. In contrast, human perception is much more robust to such …

Deep neural networks are vulnerable to adversarial examples (AEs), which have adversarial
transferability: AEs generated for the source model can mislead another (target) model's …

Today's computer vision models achieve human or near-human level performance across a
wide variety of vision tasks. However, their architectures, data, and learning algorithms differ …