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 …
T Cohen, M Welling - International conference on machine …, 2016 - proceedings.mlr.press
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 …