In this article, I hope to inspire you to start exploring satellite imagery datasets. Recently, this technology has gained huge momentum, and we are finding that new possibilities arise when we use satellite image analysis. Satellite data changes the game because it allows us to gather new information that is not readily available to businesses. Satellite images allow you to view Earth from a broader perspective. You can point to any location on Earth and get the latest satellite images of that area. Also, this information is easy to access.

Ongoing studies have identified similarities between neural representations in biological networks and in deep artificial neural networks. This has led to renewed interest in developing analogies between the backpropagation learning algorithm used to train artificial networks and the synaptic plasticity rules operative in the brain. These efforts are challenged by biologically implausible features of backpropagation, one of which is a reliance on symmetric forward and backward synaptic weights. A number of methods have been proposed that do not rely on weight symmetry but, thus far, these have failed to scale to deep convolutional networks and complex data. We identify principal obstacles to the scalability of such algorithms and introduce several techniques to mitigate them. We demonstrate that a modification of the feedback alignment method that enforces a weaker form of weight symmetry, one that requires agreement of weight sign but not magnitude, can achieve performance competitive with backpropagation. Our results complement those of Bartunov et al. (2018) and Xiao et al. (2018b) and suggest that mechanisms that promote alignment of feedforward and feedback weights are critical for learning in deep networks.

Chris Lister, vice president of operations of the Tesla Gigafactory, provides insight during a tour on Dec. 3, 2018. Big numbers are one way to appreciateTesla's gargantuan Nevada Gigafactory. Operating 24-hours per day in shifts, workers produce enough battery packs and drive units in a week to power 5,300 of Tesla's Model 3 sedans. Tesla says at 5.4 million square feet, roughly equivalent to 50 Home Depot stores, the factory is just 30 percent of its potential size and is already producing more batteries than all other carmakers combined. With more than 7,000 Tesla workers, the factory is responsible for increasing manufacturing employment in the Reno-Sparks area by 55 percent since 2014, according to the Governor's Office of Economic Development.

Consider a family $Z=\{\boldsymbol{x_{i}},y_{i}$,$1\leq i\leq N\}$ of $N$ pairs of vectors $\boldsymbol{x_{i}} \in \mathbb{R}^d$ and scalars $y_{i}$ that we aim to predict for a new sample vector $\mathbf{x}_0$. Kriging models $y$ as a sum of a deterministic function $m$, a drift which depends on the point $\boldsymbol{x}$, and a random function $z$ with zero mean. The zonality hypothesis interprets $y$ as a weighted sum of $d$ random functions of a single independent variables, each of which is a kriging, with a quadratic form for the variograms drift. We can therefore construct an unbiased estimator $y^{*}(\boldsymbol{x_{0}})=\sum_{i}\lambda^{i}z(\boldsymbol{x_{i}})$ de $y(\boldsymbol{x_{0}})$ with minimal variance $E[y^{*}(\boldsymbol{x_{0}})-y(\boldsymbol{x_{0}})]^{2}$, with the help of the known training set points. We give the explicitly closed form for $\lambda^{i}$ without having calculated the inverse of the matrices.

We introduce and analyse two algorithms for exploration-exploitation in discrete and continuous Markov Decision Processes (MDPs) based on exploration bonuses. SCAL$^+$ is a variant of SCAL (Fruit et al., 2018) that performs efficient exploration-exploitation in any unknown weakly-communicating MDP for which an upper bound C on the span of the optimal bias function is known. For an MDP with $S$ states, $A$ actions and $\Gamma \leq S$ possible next states, we prove that SCAL$^+$ achieves the same theoretical guarantees as SCAL (i.e., a high probability regret bound of $\widetilde{O}(C\sqrt{\Gamma SAT})$), with a much smaller computational complexity. Similarly, C-SCAL$^+$ exploits an exploration bonus to achieve sublinear regret in any undiscounted MDP with continuous state space. We show that C-SCAL$^+$ achieves the same regret bound as UCCRL (Ortner and Ryabko, 2012) while being the first implementable algorithm with regret guarantees in this setting. While optimistic algorithms such as UCRL, SCAL or UCCRL maintain a high-confidence set of plausible MDPs around the true unknown MDP, SCAL$^+$ and C-SCAL$^+$ leverage on an exploration bonus to directly plan on the empirically estimated MDP, thus being more computationally efficient.

Although a key driver of Earth's climate system, global land-atmosphere energy fluxes are poorly constrained. Here we use machine learning to merge energy flux measurements from FLUXNET eddy covariance towers with remote sensing and meteorological data to estimate net radiation, latent and sensible heat and their uncertainties. The resulting FLUXCOM database comprises 147 global gridded products in two setups: (1) 0.0833${\deg}$ resolution using MODIS remote sensing data (RS) and (2) 0.5${\deg}$ resolution using remote sensing and meteorological data (RS+METEO). Within each setup we use a full factorial design across machine learning methods, forcing datasets and energy balance closure corrections. For RS and RS+METEO setups respectively, we estimate 2001-2013 global (${\pm}$ 1 standard deviation) net radiation as 75.8${\pm}$1.4 ${W\ m^{-2}}$ and 77.6${\pm}$2 ${W\ m^{-2}}$, sensible heat as 33${\pm}$4 ${W\ m^{-2}}$ and 36${\pm}$5 ${W\ m^{-2}}$, and evapotranspiration as 75.6${\pm}$10 ${\times}$ 10$^3$ ${km^3\ yr^{-1}}$ and 76${\pm}$6 ${\times}$ 10$^3$ ${km^3\ yr^{-1}}$. FLUXCOM products are suitable to quantify global land-atmosphere interactions and benchmark land surface model simulations.

Abstract--In this paper we consider the problem of modelbased learningof turbulent flows using mobile robots. The key idea is to use empirical data to improve on numerical estimates of time-averaged flow properties that can be obtained using Reynolds-Averaged Navier Stokes (RANS) models. RANS models are computationally efficient and provide global knowledge of the flow but they also rely on simplifying assumptions and require experimental validation. In this paper, we instead construct statistical models of the flow properties using Gaussian Processes (GPs) and rely on the numerical solutions obtained from RANS models to inform their mean. We then utilize Bayesian inference to incorporate empirical measurements of the flow into these GPs, specifically, measurements of the time-averaged velocity and turbulent intensity fields. Moreover, it accounts for measurement noise by systematically incorporating it in the GP models. To obtain the velocity and turbulent intensity measurements, we design a cost-effective mobile robot sensor that collects and analyzes instantaneous velocity readings. We control this mobile robot through a sequence of waypoints that maximize the information content of the corresponding measurements. The end result is a posterior distribution of the flow field that better approximates the real flow and also quantifies the uncertainty in the flow properties. We present experimental results that demonstrate considerable improvement in the prediction of the flow properties compared to pure numerical simulations. I. INTRODUCTION Knowledge of turbulent flow properties, e.g., velocity and turbulent intensity, is of paramount importance for many engineering applications.At larger scales, these properties are used for the study of ocean currents and their effects on aquatic life, [1], [2], [3], meteorology, [4], bathymetry, [5], and localization of atmospheric pollutants, [6], to name a few. At smaller scales, knowledge of flow fields is important in applications ranging from optimal HVAC of residential buildings for human comfort, [7], to design of drag-efficient bodies in aerospace and automotive industries, [8]. At even smaller scales, the characteristics of velocity fluctuations in vessels are important for vascular pathology and diagnosis, [9] or for the control of bacteria-inspired uniflagellar robots, [10]. Another important application that requires global knowledge of the velocity field is chemical source identification in advection-diffusion transport systems, [11], [12], [13].

Non-intrusive load monitoring or energy disaggregation involves estimating the power consumption of individual appliances from measurements of the total power consumption of a home. Deep neural networks have been shown to be effective for energy disaggregation. In this work, we present a deep neural network architecture which achieves state of the art disaggregation performance with substantially improved computational efficiency, reducing model training time by a factor of 32 and prediction time by a factor of 43. This improvement in efficiency could be especially useful for applications where disaggregation must be performed in home on lower power devices, or for research experiments which involve training a large number of models.

Robots are increasingly used to carry out critical missions in extreme environments that are hazardous for humans. This requires a high degree of operational autonomy under uncertain conditions, and poses new challenges for assuring the robot's safety and reliability. In this paper, we develop a framework for probabilistic model checking on a layered Markov model to verify the safety and reliability requirements of such robots, both at pre-mission stage and during runtime. Two novel estimators based on conservative Bayesian inference and imprecise probability model with sets of priors are introduced to learn the unknown transition parameters from operational data. We demonstrate our approach using data from a real-world deployment of unmanned underwater vehicles in extreme environments.

Fifty years ago today, Doug Engelbart showed 2,000 people a preview of the future. Engelbart gave a demonstration of the "oN-Line System" at the Fall Joint Computer Conference in San Francisco on Dec. 9, 1968. The oN-Line System was the first hypertext system, preceding the web by more than 20 years. But it was so much more than that. When Engelbart typed a word, it appeared simultaneously on his screen in San Francisco and on a terminal screen at the Stanford Research Institute in Menlo Park.