In neural networks literature, there is a strong interest in identifying and defining activation
functions which can improve neural network performance. In recent years there has been a …

Artificial neural networks (ANNs) have undergone a revolution, catalyzed by better
supervised learning algorithms. However, in stark contrast to young animals (including …

In self-supervised representation learning, a common idea behind most of the state-of-the-
art approaches is to enforce the robustness of the representations to predefined …

Priors are essential for reconstructing images from noisy and/or incomplete measurements.
The choice of the prior determines both the quality and uncertainty of recovered images. We …

Recent work has identified dozens of non-coding loci for Alzheimer's disease (AD) risk, but
their mechanisms and AD transcriptional regulatory circuitry are poorly understood. Here …

In recent years, deep learning has revolutionized the field of machine learning, for computer
vision in particular. In this approach, a deep (multilayer) artificial neural network (ANN) is …

We perform a careful, thorough, and large scale empirical study of the correspondence
between wide neural networks and kernel methods. By doing so, we resolve a variety of …

The integration of data and scientific computation is driving a paradigm shift across the
engineering, natural, and physical sciences. Indeed, there exists an unprecedented …

Steganography is the practice of concealing a secret message within another, ordinary,
message. Commonly, steganography is used to unobtrusively hide a small message within …

A central goal of neuroscience is to understand the representations formed by brain activity
patterns and their connection to behaviour. The classic approach is to investigate how …