The paper reviews and extends an emerging body of theoretical results on deep learning
including the conditions under which it can be exponentially better than shallow learning. A …

Current learning machines have successfully solved hard application problems, reaching
high accuracy and displaying seemingly intelligent behavior. Here we apply recent …

Seismic velocity is one of the most important parameters used in seismic exploration.
Accurate velocity models are the key prerequisites for reverse time migration and other high …

Scene representation—the process of converting visual sensory data into concise
descriptions—is a requirement for intelligent behavior. Recent work has shown that neural …

Recent progress in artificial intelligence has renewed interest in building systems that learn
and think like people. Many advances have come from using deep neural networks trained …

Deep neural networks have achieved impressive experimental results in image
classification, but can surprisingly be unstable with respect to adversarial perturbations, that …

Abstract We introduce Group equivariant Convolutional Neural Networks (G-CNNs), a
natural generalization of convolutional neural networks that reduces sample complexity by …

Neuroscience has focused on the detailed implementation of computation, studying neural
codes, dynamics and circuits. In machine learning, however, artificial neural networks tend …

It has long been recognized that the invariance and equivariance properties of a
representation are critically important for success in many vision tasks. In this paper we …

Highlights•Novelty-based exploration can expedite learning when rewards are
sparse.•Novelty-based machine learning incorporates novelty into computations of value.•In …