Recent work has introduced a simple numerical method for solving partial differential equations (PDEs) with deep neural networks (DNNs). This paper reviews and extends the method while applying it to analyze one of the most fundamental features in numerical PDEs and nonlinear analysis: irregular solutions. First, the Sod shock tube solution to compressible Euler equations is discussed, analyzed, and then compared to conventional finite element and finite volume methods. These methods are extended to consider performance improvements and simultaneous parameter space exploration. Next, a shock solution to compressible magnetohydrodynamics (MHD) is solved for, and used in a scenario where experimental data is utilized to enhance a PDE system that is \emph{a priori} insufficient to validate against the observed/experimental data. This is accomplished by enriching the model PDE system with source terms and using supervised training on synthetic experimental data. The resulting DNN framework for PDEs seems to demonstrate almost fantastical ease of system prototyping, natural integration of large data sets (be they synthetic or experimental), all while simultaneously enabling single-pass exploration of the entire parameter space.

We present a fully-supervized method for learning to segment data structured by an adjacency graph. We introduce the graph-structured contrastive loss, a loss function structured by a ground truth segmentation. It promotes learning vertex embeddings which are homogeneous within desired segments, and have high contrast at their interface. Thus, computing a piecewise-constant approximation of such embeddings produces a graph-partition close to the objective segmentation. This loss is fully backpropagable, which allows us to learn vertex embeddings with deep learning algorithms. We evaluate our methods on a 3D point cloud oversegmentation task, defining a new state-of-the-art by a large margin. These results are based on the published work of Landrieu and Boussaha 2019.

One of the most radioactive places on Earth has been mapped in unprecedented detail, thanks to a team of British scientists equipped with the latest in drone technology. Chernobyl's Red Forest remains highly irradiated 33 years on from the catastrophic accident at the number-4 nuclear reactor. Experts led by the UK's National Centre for Nuclear Robotics and the University of Bristol used drones fitted with custom-built radiation detectors to create 3D maps of the area, some of which lies just 1,600ft (500m) from the power plant. Their efforts revealed previously undetected radiation'hotspots', where radioactive material from the fallout has gathered over the years. Around 70,000 tourists visited the Chernobyl exclusion zone last year, which stretches over 1,000 square miles (2,600 sq km).

The U.S. says it will have the world's fastest supercomputer ready in just two years. The U.S. Department of Energy says it has signed a contract with Cray Inc. and Advanced Micro Devices (AMD) to build a machine called Frontier, capable of computing at 1.5 exaflops -- a level 50 times faster than current supercomputers. The department says its endeavor, which entails a $600 million investment for the development of technology and systems, will help yield new advances in artificial intelligence, machine learning, and more. Frontier will take computers U.S. computers into the exascale, and will be as powerful as the next 160 fastest supercomputers combined'Frontier's record-breaking performance will ensure our country's ability to lead the world in science that improves the lives and economic prosperity of all Americans and the entire world,' said U.S. Secretary of Energy, Rick Perry. 'Frontier will accelerate innovation in AI by giving American researchers world-class data and computing resources to ensure the next great inventions are made in the United States.' According to the U.S. Department of Energy, Frontier, which will be housed at a laboratory in Oak Ridge, Tennessee, will be able to exceed one quintillion calculations per second, as reported by The Verge -- that's as much processing power as the next 160 fastest supercomputer combined, said AMD.

During the last decade, Convolutional Neural Networks (CNNs) have become the de facto standard for various Computer Vision and Machine Learning operations. CNNs are feed-forward Artificial Neural Networks (ANNs) with alternating convolutional and subsampling layers. Deep 2D CNNs with many hidden layers and millions of parameters have the ability to learn complex objects and patterns providing that they can be trained on a massive size visual database with ground-truth labels. With a proper training, this unique ability makes them the primary tool for various engineering applications for 2D signals such as images and video frames. Yet, this may not be a viable option in numerous applications over 1D signals especially when the training data is scarce or application-specific. To address this issue, 1D CNNs have recently been proposed and immediately achieved the state-of-the-art performance levels in several applications such as personalized biomedical data classification and early diagnosis, structural health monitoring, anomaly detection and identification in power electronics and motor-fault detection. Another major advantage is that a real-time and low-cost hardware implementation is feasible due to the simple and compact configuration of 1D CNNs that perform only 1D convolutions (scalar multiplications and additions). This paper presents a comprehensive review of the general architecture and principals of 1D CNNs along with their major engineering applications, especially focused on the recent progress in this field. Their state-of-the-art performance is highlighted concluding with their unique properties. The benchmark datasets and the principal 1D CNN software used in those applications are also publically shared in a dedicated website.

Abstract--In this paper, we propose a novel adaptive kernel for the radial basis function (RBF) neural networks. In [12] a novel RBF network with the multi-kernel is proposed to obtain an optimized and I. INTRODUCTION The unknown centres of the multikernels The RBF neural networks have shown excellent performance are determined by an improved k-means clustering in a number of problems of practical interest. An orthogonal least squares (OLS) algorithm is reservoirs of brine are analyzed for physicochemical properties used to determine the remaining parameters. The convergence of the ACA is analyzed by the [3] the RBF kernel is used to predict the pressure gradient Lyapunov criterion. In the context of nuclear physics, RBF Cognitive Radial Basis Function network (McRBFN) and its has been effectively used to model the stopping power data Projection based Learning (PBL) referred to as PBL-McRBFN of materials as in [4].

For instance, dual arm manipulators have been effectively employed in a diversity of tasks including assembling a car, grasping and transporting an object or nursing the elderly [7]. In those scenarios, the DAR have been expected to behave like a human, which is they should be able to manipulate an object similarly to what a person does [3]. As compared to a single arm robot, the DAR have significant advantages such as more flexible movements, higher precision and greater dexterity for handling large objects [8, 9]. Nevertheless, since the kinematic and dynamic models of the DAR system are much more complicated than those of a single arm robot, it has more challenges to effectively and efficiently control the DAR, where synchronously coordinating the robot arms are highly expected. In order to accurately and stabily track the robot arms along desired trajectories, a number of the control strategies have been proposed. For instance, the traditional methods such as nonlinear feedback control [10] or hybrid force/position control relied on the kinematics and statics [11, 12] have been proposed to simultaneously control both of the arms. In the works [13, 14, 15], the authors have proposed to utilize the impedance control by considering the dynamic interaction between the robot and its surrounding environment while guaranteeing the desired movements. More importantly, robustness of the control performance is also highly prioritized in consideration of designing a controller for a highly uncertain and nonlinear DAR system. In literature of the modern control theory, sliding mode control (SMC) demonstrates a diverse ability to robustly control any system.

Evolution and learning are two of the fundamental mechanisms by which life adapts in order to survive and to transcend limitations. These biological phenomena inspired successful computational methods such as evolutionary algorithms and deep learning. Evolution relies on random mutations and on random genetic recombination. Here we show that learning to evolve, i.e. learning to mutate and recombine better than at random, improves the result of evolution in terms of fitness increase per generation and even in terms of attainable fitness. We use deep reinforcement learning to learn to dynamically adjust the strategy of evolutionary algorithms to varying circumstances. Our methods outperform classical evolutionary algorithms on combinatorial and continuous optimization problems.

University of Southern California (Los Angeles, CA): Developing novel data-driven predictive models for integration into real-time fault detection and diagnosis, and integrate those models by using predictive control algorithms to improve the efficiency of energy production operations in a geothermal power plant. The project will develop deep dynamic neural networks for fault prediction and predictive process control workflows to improve the efficiency of geothermal operations. Upflow Limited (Taupo, New Zealand): Making available multiple decades of closely-guarded production data from one of the world's longest operating geothermal fields, and combining it with the archives from the largest geothermal company operating in the U.S. Models developed from this massive data store will enable the creation of a prediction/recommendation engine that will help operators improve plant availability. Colorado School of Mines (Golden, CO): Applying new machine learning techniques to analyze remote-sensing images, with the goal of developing a process to identify the presence of blind geothermal resources based on surface characteristics. Colorado School of Mines will develop a methodology to automatically label data from hyperspectral images of Brady's Hot Springs, Desert Rock, and the Salton Sea.

Bayesian Optimization using Gaussian Processes is a popular approach to deal with the optimization of expensive black-box functions. However, because of the a priori on the stationarity of the covariance matrix of classic Gaussian Processes, this method may not be adapted for non-stationary functions involved in the optimization problem. To overcome this issue, a new Bayesian Optimization approach is proposed. It is based on Deep Gaussian Processes as surrogate models instead of classic Gaussian Processes. This modeling technique increases the power of representation to capture the non-stationarity by simply considering a functional composition of stationary Gaussian Processes, providing a multiple layer structure. This paper proposes a new algorithm for Global Optimization by coupling Deep Gaussian Processes and Bayesian Optimization. The specificities of this optimization method are discussed and highlighted with academic test cases. The performance of the proposed algorithm is assessed on analytical test cases and an aerospace design optimization problem and compared to the state-of-the-art stationary and non-stationary Bayesian Optimization approaches.