Science has always relied on a combination of approaches to derive an answer or develop a theory. The seeds for Darwin's theory of natural selection grew under a Herculean aggregation of observation, data, and experiment. The more recent confirmation of gravitational waves by the Laser Interferometer Gravitational-Wave Observatory (LIGO) was a decades-long interplay of theory, experiment, and computation. Certainly, this idea was not lost on the U.S. Department of Energy's (DOE) Argonne National Laboratory, which has helped advance the boundaries of high-performance computing technologies through the Argonne Leadership Computing Facility (ALCF). Realizing the promise of exascale computing, the ALCF is developing the framework by which to harness this immense computing power to an advanced combination of simulation, data analysis, and machine learning.

Experiments at the Large Hadron Collider (LHC), the world's largest particle accelerator at the European particle physics lab CERN, produce about a million gigabytes of data every second. Even after reduction and compression, the data amassed in just one hour is similar to the data volume Facebook collects in an entire year – too much to store and analyze. Luckily, particle physicists don't have to deal with all of that data all by themselves. They partner with a form of artificial intelligence called machine learning that learns how to do complex analyses on its own. A group of researchers, including scientists at the Department of Energy's SLAC National Accelerator Laboratory and Fermi National Accelerator Laboratory, summarize current applications and future prospects of machine learning in particle physics in a paper published today in Nature.

Machine learning software accounts for a significant amount of energy consumed in data centers. These algorithms are usually optimized towards predictive performance, i.e. accuracy, and scalability. This is the case of data stream mining algorithms. Although these algorithms are adaptive to the incoming data, they have fixed parameters from the beginning of the execution. We have observed that having fixed parameters lead to unnecessary computations, thus making the algorithm energy inefficient. In this paper we present the nmin adaptation method for Hoeffding trees. This method adapts the value of the nmin parameter, which significantly affects the energy consumption of the algorithm. The method reduces unnecessary computations and memory accesses, thus reducing the energy, while the accuracy is only marginally affected. We experimentally compared VFDT (Very Fast Decision Tree, the first Hoeffding tree algorithm) and CVFDT (Concept-adapting VFDT) with the VFDT-nmin (VFDT with nmin adaptation). The results show that VFDT-nmin consumes up to 27% less energy than the standard VFDT, and up to 92% less energy than CVFDT, trading off a few percent of accuracy in a few datasets.

Multi-Task Gaussian processes (MTGPs) have shown a significant progress both in expressiveness and interpretation of the relatedness between different tasks: from linear combinations of independent single-output Gaussian processes (GPs), through the direct modeling of the cross-covariances such as spectral mixture kernels with phase shift, to the design of multivariate covariance functions based on spectral mixture kernels which model delays among tasks in addition to phase differences, and which provide a parametric interpretation of the relatedness across tasks. In this paper we further extend expressiveness and interpretability of MTGPs models and introduce a new family of kernels capable to model nonlinear correlations between tasks as well as dependencies between spectral mixtures, including time and phase delay. Specifically, we use generalized convolution spectral mixture kernels for modeling dependencies at spectral mixture level, and coupling coregionalization for discovering task level correlations. The proposed kernels for MTGP are validated on artificial data and compared with existing MTGPs methods on three real-world experiments. Results indicate the benefits of our more expressive representation with respect to performance and interpretability.

Bad debt control can be considered a use case under the umbrella of revenue protection. It can result in hard dollar value, making it easier to show the benefits of the project. Different types of revenue protection projects, such as power theft, unaccounted energy, fraud, and bad debt require different methods to identify the issues. The majority of approaches are rule based detections, however, others use machine learning models. For example, a machine learning model can be used to generate credit risk scores for customers.

Here's where to search between a soccer pitch, gas station and stunt mountain in Fortnite: Battle Royale.Credit: Epic / Erik Kain Fortnite's Season 5, Week 4 challenges are live. Once again, players are tasked with searching between three points---this time in the northwest section of the map just south of Pleasant Park and to the west of Loot Lake. For this week's challenge we'll need to search between a gas station, a soccer pitch and a stunt mountain. There are a number of soccer fields around the map, but one of the most prominent is located in the southern end of Pleasant Park. This is the soccer pitch you're looking for.

Experiments at the Large Hadron Collider produce about a million gigabytes of data every second. Even after reduction and compression, the data amassed in just one hour at the LHC is similar to the data volume Facebook collects in an entire year. Luckily, particle physicists don't have to deal with all of that data all by themselves. They partner with a form of artificial intelligence that learns how to do complex analyses on its own, called machine learning. "Compared to a traditional computer algorithm that we design to do a specific analysis, we design a machine learning algorithm to figure out for itself how to do various analyses, potentially saving us countless man-hours of design and analysis work," says College of William & Mary physicist Alexander Radovic, who works on the NOvA neutrino experiment.

Imagine a world where you can play the role of an engineer virtually troubleshooting simple problems with your boiler through augmented reality, or where your digital assistant can arrange a boiler service at a convenient time. Imagine the cost savings and environmental benefits of factories that remotely control their electricity use to avoid peak times. These scenarios are quickly becoming a reality through the power of Artificial Intelligence. Once limited to laboratories and science fiction, AI is now part of our everyday lives. From simple Machine Learning that recommends what we buy on Amazon to the cutting-edge Deep Learning behind the emergence of driverless cars, AI is transforming everything we do.

You have access to this full article to experience the outstanding content available to SPE members and JPT subscribers. To ensure continued access to JPT's content, please Sign In, JOIN SPE, or Subscribe to JPT Marine mining initiatives open a new field of subsea operations. Offshore oil and gas sites are still located primarily in areas where divers can support maintenance and repair requirements, but future marine mining will take place in greater depths and with a complexity of machines that requires support from robotic systems equipped with a substantial amount of artificial intelligence (AI). Technologies are being developed that have the potential to support marine mining in all stages from prospection to decommissioning. These developments will likely have substantial influence in the oil and gas industry, itself searching for ways to maximize exploitation of assets.

Given a set of human's decisions that are observed, inverse optimization has been developed and utilized to infer the underlying decision making problem. The majority of existing studies assumes that the decision making problem is with a single objective function, and attributes data divergence to noises, errors or bounded rationality, which, however, could lead to a corrupted inference when decisions are tradeoffs among multiple criteria. In this paper, we take a data-driven approach and design a more sophisticated inverse optimization formulation to explicitly infer parameters of a multiobjective decision making problem from noisy observations. This framework, together with our mathematical analyses and advanced algorithm developments, demonstrates a strong capacity in estimating critical parameters, decoupling "interpretable" components from noises or errors, deriving the denoised \emph{optimal} decisions, and ensuring statistical significance. In particular, for the whole decision maker population, if suitable conditions hold, we will be able to understand the overall diversity and the distribution of their preferences over multiple criteria, which is important when a precise inference on every single decision maker is practically unnecessary or infeasible. Numerical results on a large number of experiments are reported to confirm the effectiveness of our unique inverse optimization model and the computational efficacy of the developed algorithms.