Long short-term memory (LSTM) The long short-term memory (LSTM) is a special kind of recurrent neural network (Gers et al., 1999; Hochreiter & Schmidhuber, 1997), and is capable of processing sequential data with correlations between points that are far apart. On the one hand, similar to the standard recurrent neural network, the LSTM has a self-looped structure that allows the result of the previous step to participate in the calculation of the subsequent step. On the other hand, the LSTM possesses four interaction layers in its neurons, which makes it able to forget useless information and learn correlations between data points that are far away from each other in sequence. The LSTM is the state-of-the-art model for well log generation in previous studies (Zhang et al., 2018). This agrees well with the perspective of geoscience, since the well logs reflect a formation condition, which possesses internal continuity (spatial dependency). The sequential information in reservoirs is critical for well logs generation. Therefore, the LSTM constitutes the ideal foundation for building a new model for this type of geoscience problem.

Statistical methods for the analysis and forecasting of time series data have a long history (Tsay, 2000). The well-accepted Box-Jenkins analysis and forecasting methods have been applied in a wide range of applications, from finance to medicine, and the classic book that laid out the theory is now in its fourth edition with over 55,000 citations (Box et al., 2015). In this paper, we focus on the specialized area of time series regression where the goal is to predict one time series with the help of covariates that include elements which also have a time series nature. Some authors refer to this as dynamic regression (Hyndman and Athanasopoulos, 2018), others use the term regARIMA (Gómez and Maravall, 1994; Maravall et al., 2016). Pankratz (2012) provides an excellent overview.

We propose a simple method to generate large amounts of multilingual question and answer pairs by a single generative model. These synthetic samples are then applied to augment the available gold multilingual ones to improve the performance of multilingual QA models on target languages. Our approach only requires existence of automatically translated samples from English to the target domain, thus removing the need for human annotations in the target languages. Experimental results show our proposed approach achieves significant gains in a number of multilingual datasets.

As more and more industries take on artificial intelligence to solve some of their biggest challenges, can machines help us understand and fix climate change issues? So your phone recognises your face, and your bank can block any transaction unlike your spending habits. And your online supermarket nudges you with their vegan products just because you've bought that oat milk once, while your online movie platform keeps throwing B-movies at you after you watched that soap opera last month. A growing number of our devices and services are relying on artificial intelligence (AI), a technology that continues to branch out and pop up in more and more areas of our lives. Scientists, entrepreneurs, and governments are leveraging AI to explore solutions for some of society's biggest challenges.

Autonomous things (AuT), or the Internet of autonomous things (IoAT), is a rising term for the innovative advancements that are expected to carry computers into the physical environment as autonomous entities without human guidance, openly moving and collaborating with people and different items. AuTs are stocked with sensors, AI and analytical abilities to improve the things they can do. With that impact, each machine can settle on its own choice and complete tasks autonomously. These gadgets are fit for working independently. Autonomous devices need to interface with their environmental surroundings to stay away from accidents.

Benjamin Tee has long been captivated by a scene in "Star Wars: The Empire Strikes Back" where the surgical droid 2-1B replaces Luke Skywalker's hand after Darth Vader slices it off with a lightsaber in a battle on Cloud City. A fully autonomous robot surgeon is the Holy Grail--and many years off, says Dr. Tee, assistant professor of materials science and engineering at the National University of Singapore. He and other researchers are developing devices that can perform surgical tasks with minimal human oversight. Dr. Tee's latest project is an "artificial skin" that would give robots a sense of touch, allowing them to do things like differentiate between healthy tissue and tumors and make surgical incisions. Other researchers are working on robots that stitch up incisions and navigate to repair organs.

Music preferences are strongly shaped by the cultural and socio-economic background of the listener, which is reflected, to a considerable extent, in country-specific music listening profiles. Previous work has already identified several country-specific differences in the popularity distribution of music artists listened to. In particular, what constitutes the "music mainstream" strongly varies between countries. To complement and extend these results, the article at hand delivers the following major contributions: First, using state-of-the-art unsupervised learning techniques, we identify and thoroughly investigate (1) country profiles of music preferences on the fine-grained level of music tracks (in contrast to earlier work that relied on music preferences on the artist level) and (2) country archetypes that subsume countries sharing similar patterns of listening preferences. Second, we formulate four user models that leverage the user's country information on music preferences. Among others, we propose a user modeling approach to describe a music listener as a vector of similarities over the identified country clusters or archetypes. Third, we propose a context-aware music recommendation system that leverages implicit user feedback, where context is defined via the four user models. More precisely, it is a multi-layer generative model based on a variational autoencoder, in which contextual features can influence recommendations through a gating mechanism. Fourth, we thoroughly evaluate the proposed recommendation system and user models on a real-world corpus of more than one billion listening records of users around the world (out of which we use 369 million in our experiments) and show its merits vis-a-vis state-of-the-art algorithms that do not exploit this type of context information.

As organizations gain more experience deploying machine learning (ML) and artificial intelligence (AI) across different parts of the business, they're discovering new and interesting ways to use the technology. Typical use cases include established applications such as personalization, fraud detection, and speech recognition. But there's much more to explore. "The cloud enables extremely low-cost compute and storage, which opens up opportunities for more modeling," says Sri Elaprolu, senior leader, Amazon Machine Learning Solutions Lab. "There's lots of innovation yet to happen. We are barely scratching the surface."

Operating Earth observing satellites requires efficient planning methods that coordinate activities of multiple spacecraft. The satellite task planning problem entails selecting actions that best satisfy mission objectives for autonomous execution. Task scheduling is often performed by human operators assisted by heuristic or rule-based planning tools. This approach does not efficiently scale to multiple assets as heuristics frequently fail to properly coordinate actions of multiple vehicles over long horizons. Additionally, the problem becomes more difficult to solve for large constellations as the complexity of the problem scales exponentially in the number of requested observations and linearly in the number of spacecraft. It is expected that new commercial optical and radar imaging constellations will require automated planning methods to meet stated responsiveness and throughput objectives. This paper introduces a new approach for solving the satellite scheduling problem by generating an infeasibility-based graph representation of the problem and finding a maximal independent set of vertices for the graph. The approach is tested on a scenarios of up to 10,000 requested imaging locations for the Skysat constellation of optical satellites as well as simulated constellations of up to 24 satellites. Performance is compared with contemporary graph-traversal and mixed-integer linear programming approaches. Empirical results demonstrate improvements in both the solution time along with the number of scheduled collections beyond baseline methods. For large problems, the maximum independent set approach is able find a feasible schedule with 8% more collections in 75% less time.

Traditional deep generative models of images and other spatial modalities can only generate fixed sized outputs. The generated images have exactly the same resolution as the training images, which is dictated by the number of layers in the underlying neural network. Recent work has shown, however, that feeding spatial noise vectors into a fully convolutional neural network enables both generation of arbitrary resolution output images as well as training on arbitrary resolution training images. While this work has provided impressive empirical results, little theoretical interpretation was provided to explain the underlying generative process. In this paper we provide a firm theoretical interpretation for infinite spatial generation, by drawing connections to spatial stochastic processes. We use the resulting intuition to improve upon existing spatially infinite generative models to enable more efficient training through a model that we call an infinite generative adversarial network, or $\infty$-GAN. Experiments on world map generation, panoramic images and texture synthesis verify the ability of $\infty$-GAN to efficiently generate images of arbitrary size.