We propose a new method to efficiently compute load-flows (the steady-state of the power-grid for given productions, consumptions and grid topology), substituting conventional simulators based on differential equation solvers. We use a deep feed-forward neural network trained with load-flows precomputed by simulation. Our architecture permits to train a network on so-called "n-1" problems, in which load flows are evaluated for every possible line disconnection, then generalize to "n-2" problems without retraining (a clear advantage because of the combinatorial nature of the problem). To that end, we developed a technique bearing similarity with "dropout", which we named "guided dropout".

Tesla will partner with French renewable energy company Neoen to build the 100-megawatt battery farm in South Australia state. After a successful run selling hats, billionaire Elon Musk's The Boring Company has expanded its offering to include flamethrowers. Musk announced that his infrastructure firm had started selling flamethrowers Sunday. People were able to pre-order them for $500 each, and could buy an "overpriced" fire extinguisher with a "cool sticker" for £30 as well. A flamethrower being offered for sale by Elon Musk and The Boring Company.

In this talk we will present the various optimization problems encountered in smart grids from the production, transmission and distribution of energy as well as the demand side management in smart homes and the pricing of energy. The optimization opportunities are highlighted for metaheuristics, multi-objective optimization, optimization under uncertainty, optimization-simulation, optimization-machine learning and multi-level optimization.

This paper surveys the current state of the art in Natural Language Generation (NLG), defined as the task of generating text or speech from non-linguistic input. A survey of NLG is timely in view of the changes that the field has undergone over the past decade or so, especially in relation to new (usually data-driven) methods, as well as new applications of NLG technology. This survey therefore aims to (a) give an up-to-date synthesis of research on the core tasks in NLG and the architectures adopted in which such tasks are organised; (b) highlight a number of relatively recent research topics that have arisen partly as a result of growing synergies between NLG and other areas of artificial intelligence; (c) draw attention to the challenges in NLG evaluation, relating them to similar challenges faced in other areas of Natural Language Processing, with an emphasis on different evaluation methods and the relationships between them.

Structural and topological information play a key role in modeling flow and transport through fractured rock in the subsurface. Discrete fracture network (DFN) computational suites such as dfnWorks are designed to simulate flow and transport in such porous media. Flow and transport calculations reveal that a small backbone of fractures exists, where most flow and transport occurs. Restricting the flowing fracture network to this backbone provides a significant reduction in the network's effective size. However, the particle tracking simulations needed to determine the reduction are computationally intensive. Such methods may be impractical for large systems or for robust uncertainty quantification of fracture networks, where thousands of forward simulations are needed to bound system behavior. In this paper, we develop an alternative network reduction approach to characterizing transport in DFNs, by combining graph theoretical and machine learning methods. We consider a graph representation where nodes signify fractures and edges denote their intersections. Using random forest and support vector machines, we rapidly identify a subnetwork that captures the flow patterns of the full DFN, based primarily on node centrality features in the graph. Our supervised learning techniques train on particle-tracking backbone paths found by dfnWorks, but run in negligible time compared to those simulations. We find that our predictions can reduce the network to approximately 20% of its original size, while still generating breakthrough curves consistent with those of the original network.

Grouping objects into clusters based on similarities or weights between them is one of the most important problems in science and engineering. In this work, by extending message passing algorithms and spectral algorithms proposed for unweighted community detection problem, we develop a non-parametric method based on statistical physics, by mapping the problem to Potts model at the critical temperature of spin glass transition and applying belief propagation to solve the marginals corresponding to the Boltzmann distribution. Our algorithm is robust to over-fitting and gives a principled way to determine whether there are significant clusters in the data and how many clusters there are. We apply our method to different clustering tasks and use extensive numerical experiments to illustrate the advantage of our method over existing algorithms. In the community detection problem in weighted and directed networks, we show that our algorithm significantly outperforms existing algorithms. In the clustering problem when the data was generated by mixture models in the sparse regime we show that our method works to the theoretical limit of detectability and gives accuracy very close to that of the optimal Bayesian inference. In the semi-supervised clustering problem, our method only needs several labels to work perfectly in classic datasets. Finally, we further develop Thouless-Anderson-Palmer equations which reduce heavily the computation complexity in dense-networks but gives almost the same performance as belief propagation.

Abstract--Monge-Kantorovich distances, otherwise known as Wasserstein distances, have received a growing attention in statistics and machine learning as a powerful discrepancy measure for probability distributions. In this paper, we focus on forecasting a Gaussian process indexed by probability distributions. For this, we provide a family of positive definite kernels built using transportation based distances. We provide a probabilistic understanding of these kernels and characterize the corresponding stochastic processes. We prove that the Gaussian processes indexed by distributions corresponding to these kernels can be efficiently forecast, opening new perspectives in Gaussian process modeling. RIGINALLY used in spatial statistics (see for instance [2] and references therein), Kriging has become very popular in many fields such as machine learning or computer experiment, as described in [3]. It consists in predicting the value of a function at some point by a linear combination of observed values at different points. The unknown function is modeled as the realization of a random process, usually Gaussian, and the Kriging forecast can be seen as the posterior mean, leading to the optimal linear unbiased predictor of the random process. Gaussian process models rely on the definition of a covariance function that characterizes the correlations between values of the process at different observation points. As the notion of similarity between data points is crucial, i.e. close location inputs are likely to have similar target values, covariance functions are the key ingredient in using Gaussian processes, since they define nearness or similarity.

The OLCF's recently deployed DGX-1 artificial intelligence supercomputer by NVIDIA, featuring eight NVIDIA Tesla GPUs and NVLink technology, will offer scientists and researchers new opportunities to delve into deep learning technologies. The Oak Ridge Leadership Computing Facility (OLCF) recently deployed a new NVIDIA DGX‑1 artificial intelligence supercomputer to offer scientists and researchers opportunities to delve into deep learning technologies with more vigor than ever before. Deep learning uses neural networks to classify data or predict outcomes by training models on large data sets and by abstracting high-level features or patterns from lower level data. The OLCF is a DOE Office of Science User Facility located at ORNL. Scientists and researchers at the US Department of Energy's (DOE's) Oak Ridge National Laboratory (ORNL) are using deep learning because of its potential to leverage big data analytics to automate and accelerate the scientific discovery process.

We introduce a new unsupervised learning problem: clustering wide-sense stationary ergodic stochastic processes. A covariance-based dissimilarity measure and consistent algorithms are designed for clustering offline and online data settings, respectively. We also suggest a formal criterion on the efficiency of dissimilarity measures, and discuss of some approach to improve the efficiency of clustering algorithms, when they are applied to cluster particular type of processes, such as self-similar processes with wide-sense stationary ergodic increments. Clustering synthetic data sampled from fractional Brownian motions is provided as an example of application.

Video Friday is your weekly selection of awesome robotics videos, collected by your Automaton bloggers. We'll also be posting a weekly calendar of upcoming robotics events for the next few months; here's what we have so far (send us your events!): Let us know if you have suggestions for next week, and enjoy today's videos. ANYmal was at the World Economic Forum in Davos, where it got cold feet. Robot arm maintenance in space is much more difficult than robot arm maintenance on Earth, but you get quite the view.