Understanding dynamic fracture propagation is essential to predicting how brittle materials fail. Various mathematical models and computational applications have been developed to predict fracture evolution and coalescence, including finite-discrete element methods such as the Hybrid Optimization Software Suite (HOSS). While such methods achieve high fidelity results, they can be computationally prohibitive: a single simulation takes hours to run, and thousands of simulations are required for a statistically meaningful ensemble. We propose a machine learning approach that, once trained on data from HOSS simulations, can predict fracture growth statistics within seconds. Our method uses deep learning, exploiting the capabilities of a graph convolutional network to recognize features of the fracturing material, along with a recurrent neural network to model the evolution of these features. In this way, we simultaneously generate predictions for qualitatively distinct material properties. Our prediction for total damage in a coalesced fracture, at the final simulation time step, is within 3% of its actual value, and our prediction for total length of a coalesced fracture is within 2%. We also develop a novel form of data augmentation that compensates for the modest size of our training data, and an ensemble learning approach that enables us to predict when the material fails, with a mean absolute error of approximately 15%.

Change detection involves segmenting sequential data such that observations in the same segment share some desired properties. Multivariate change detection continues to be a challenging problem due to the variety of ways change points can be correlated across channels and the potentially poor signal-to-noise ratio on individual channels. In this paper, we are interested in locating additive outliers (AO) and level shifts (LS) in the unsupervised setting. We propose ABACUS, Automatic BAyesian Changepoints Under Sparsity, a Bayesian source separation technique to recover latent signals while also detecting changes in model parameters. Multi-level sparsity achieves both dimension reduction and modeling of signal changes. We show ABACUS has competitive or superior performance in simulation studies against state-of-the-art change detection methods and established latent variable models. We also illustrate ABACUS on two real application, modeling genomic profiles and analyzing household electricity consumption.

According to a Pegasystems' survey of 3,500 consumers from across the globe, customers are unimpressed with the performance of online chatbots. According to the latest study on the effectiveness of the popular AI tech, a lack of'intelligence' is the biggest complaint consumers have against automated bots. In fact, 65 percent of the people surveyed said they would rather speak to an actual person over a chatbot, despite claims they could be convenient in certain situations. "As chatbots become more pervasive, the quality of the engagement has lagged significantly behind customer expectations," said Ying Chen, head of product marketing and platform technologies at Pegasystems. "To truly depend on digital channels as the first line of defence in customer service, smart businesses need to unite their chatbots with the enterprise systems that can do real work – not just fetch bits of random information."

Zion Market Research (ZMR) has recently published the comprehensive and insightful report, Artificial Intelligence in Manufacturing Market: Global Industry Analysis, Size, Share, Growth, Trends, and Forecasts 2016–2024. The global Artificial Intelligence in Manufacturing Market research report is an output of a brief assessment and an extensive analysis of practical data collected from the global Artificial Intelligence in Manufacturing Market. The data are collected on the basis of industrial drifts and demands related to the services & products. The meticulously collected data offers for the process of effortless strategic planning. It also helps in creating promising business alternatives.

WEST LAFAYETTE, Ind. -- Every two seconds, sensors measuring the United States' electrical grid collect 3 petabytes of data – the equivalent of 3 million gigabytes. Data analysis on that scale is a challenge when crucial information is stored in an inaccessible database. But researchers at Purdue University are working on a solution, combining quantum algorithms with classical computing on small-scale quantum computers to speed up database accessibility. They are using data from the U.S. Department of Energy National Labs' sensors, called phasor measurement units, that collect information on the electrical power grid about voltages, currents and power generation. Because these values can vary, keeping the power grid stable involves continuously monitoring the sensors.

Today, the president signed the Music Modernization Act into law with various celebrities, including Kid Rock, Mike Love and John Rich, present. Officially named the Orrin G. Hatch Music Modernization Act, it was unanimously passed by both the House and the Senate, and streamlines the process for music licensing and updates rules about royalties for streaming music. That really happened.Kanye West wants Apple to build Trump an'iPlane' Nothing quite like pitching a hydrogen-powered plane, "made by Apple" to the President of the United States of America. Hardcore parkour.Boston Dynamics' Atlas robot shows upgraded agility in'Parkour' video This summer workout clip features a bipedal battery-powered robot that not only jogs, but hops over obstacles and up an uneven obstacle course with nary a bobble. The'bot now has enough processing power to use its legs, arms and torso to balance through the movements and power up each 40cm-high step, while using computer vision to locate the next one.

Complex industrial systems are continuously monitored by a large number of heterogenous sensors. The diversity of their operating conditions and the possible fault types make it impossible to collect enough data for learning all the possible fault patterns. The paper proposes an integrated automatic unsupervised feature learning approach for fault detection that uses healthy conditions data only for its training. The approach is based on stacked Extreme Learning Machines (namely Hierarchical, or HELM) and comprises stacked autoencoders performing unsupervised feature learning, and a one-class classifier monitoring the variations in the features to assess the health of the system. This study provides a comprehensive evaluation of HELM fault detection capability compared to other machine learning approaches, including Deep Belief Networks. The performance is first evaluated on a synthetic dataset with typical characteristics of condition monitoring data. Subsequently, the approach is evaluated on a real case study of a power plant fault. HELM demonstrates a better performance specifically in cases where several non-informative signals are included.

SAVE for desserts, curry leaves are essential condiments in any South Indian dish, almost mandatorily so. There is really no other quintessential substitute for the cuisine. Likewise, there is no other common denominator in any of the new tech products than artificial intelligence. AI is omnipresent, demanded by all application users and touted as the new mantra by large and small technology-based lifestyle or industrial players. There is even a prediction that one day, the chess grandmaster could be a machine and that unsolved mathematical theorems will be solved in the 21st century by machines.

During a special session on digitalization at the Offshore Technology Conference (OTC) earlier this year, it was clear just how much Shell's oil and gas operations were embracing a variety of digital technologies to move the business forward. Although Martijn Dekker, vice president of strategy and portfolio for Shell, emphasized the need to start with a business problem in mind rather than letting the technology push you, he also urged others in the oil and gas business to grab the value from the data they already have. "We're using the technology that's already there to create value today. We're essentially using the data we already have and creating better efficiencies," Dekker said. He stressed the importance of just jumping into the capabilities of artificial intelligence (AI) and showing the value.

Multi-objective optimization is a crucial matter in computer systems design space exploration because real-world applications often rely on a trade-off between several objectives. Derivatives are usually not available or impractical to compute and the feasibility of an experiment can not always be determined in advance. These problems are particularly difficult when the feasible region is relatively small, and it may be prohibitive to even find a feasible experiment, let alone an optimal one. We introduce a new methodology and corresponding software framework, HyperMapper 2.0, which handles multi-objective optimization, unknown feasibility constraints, and categorical/ordinal variables. This new methodology also supports injection of user prior knowledge in the search when available. All of these features are common requirements in computer systems but rarely exposed in existing design space exploration systems. The proposed methodology follows a white-box model which is simple to understand and interpret (unlike, for example, neural networks) and can be used by the user to better understand the results of the automatic search. We apply and evaluate the new methodology to automatic static tuning of hardware accelerators within the recently introduced Spatial programming language, with minimization of design runtime and compute logic under the constraint of the design fitting in a target field programmable gate array chip. Our results show that HyperMapper 2.0 provides better Pareto fronts compared to state-of-the-art baselines, with better or competitive hypervolume indicator and with 8x improvement in sampling budget for most of the benchmarks explored.