Here, we present a computer vision method based on machine learning to create population maps from satellite imagery at a global scale, with a spatial sensitivity corresponding to individual buildings and suitable for global deployment.
In this paper we propose Janus, a system which makes two major contributions to network policy abstractions. First, we extend the prior policy graph abstraction model to represent complex QoS and dynamic stateful/temporal policies. Second, we convert the policy configuration problem into an optimization problem with the goal of maximizing the number of satisfied and configured policies, and minimizing the number of path changes under dynamic environments.
In this paper we measure the extent to which situating transactions in networks can generate trust in online marketplaces with an empirical approach that provides external validity while eliminating many potential confounds.
In this work, we emphasize the importance of model explanation in various forms such as visual pointing and textual justification.
In this paper, we propose ELF, an Extensive, Lightweight and Flexible platform for fundamental reinforcement learning research.
In this paper, we analyze the optimization landscape of the random over-complete tensor decomposition problem, which has many applications in unsupervised learning, especially in learning latent variable models. In practice, it can be efficiently solved by gradient ascent on a non-convex objective.
This paper introduces a new encoder-decoder architecture that is trained to reconstruct images by disentangling the salient information of the image and the values of attributes directly in the latent space.
We introduce a novel flexible approach named Houdini for generating adversarial examples specifically tailored for the final performance measure of the task considered, be it combinatorial and non-decomposable.
We present a novel training framework for neural sequence models, particularly for grounded dialog generation.
One major obstacle towards AI is the poor ability of models to solve new problems quicker, and without forgetting previously acquired knowledge. To better understand this issue, we study the problem of continual learning, where the model observes, once and one by one, examples concerning a sequence of tasks.
