As a regression technique in spatial statistics, spatiotemporally varying coefficient model (STVC) is an important tool to discover nonstationary and interpretable response-covariate associations over both space and time. However, it is difficult to apply STVC for large-scale spatiotemporal analysis due to the high computational cost. To address this challenge, we summarize the spatiotemporally varying coefficients using a third-order tensor structure and propose to reformulate the spatiotemporally varying coefficient model as a special low-rank tensor regression problem. The low-rank decomposition can effectively model the global patterns of the large data with substantially reduced number of parameters. To further incorporate the local spatiotemporal dependencies among the samples, we place Gaussian process (GP) priors on the spatial and temporal factor matrices to better encode local spatial and temporal processes on each factor component. We refer to the overall framework as Bayesian Kernelized Tensor Regression (BKTR). For model inference, we develop an efficient Markov chain Monte Carlo (MCMC) algorithm, which uses Gibbs sampling to update factor matrices and slice sampling to update kernel hyperparameters. We conduct extensive experiments on both synthetic and real-world data sets, and our results confirm the superior performance and efficiency of BKTR for model estimation and parameter inference.

In this study, we examine a set of primary data collected from 484 students enrolled in a large public university in the Mid-Atlantic United States region during the early stages of the COVID-19 pandemic. The data, called Ties data, included students' demographic and support network information. The support network data comprised of information that highlighted the type of support, (i.e. emotional or educational; routine or intense). Using this data set, models for predicting students' academic achievement, quantified by their self-reported GPA, were created using Chi-Square Automatic Interaction Detection (CHAID), a decision tree algorithm, and cforest, a random forest algorithm that uses conditional inference trees. We compare the methods' accuracy and variation in the set of important variables suggested by each algorithm. Each algorithm found different variables important for different student demographics with some overlap. For White students, different types of educational support were important in predicting academic achievement, while for non-White students, different types of emotional support were important in predicting academic achievement. The presence of differing types of routine support were important in predicting academic achievement for cisgender women, while differing types of intense support were important in predicting academic achievement for cisgender men.

Interest in Artificial Intelligence (AI) and its applications has seen unprecedented growth in the last few years. This success can be partly attributed to the advancements made in the sub-fields of AI such as machine learning, computer vision, and natural language processing. Much of the growth in these fields has been made possible with deep learning, a sub-area of machine learning that uses artificial neural networks. This has created significant interest in the integration of vision and language. In this survey, we focus on ten prominent tasks that integrate language and vision by discussing their problem formulation, methods, existing datasets, evaluation measures, and compare the results obtained with corresponding state-of-the-art methods. Our efforts go beyond earlier surveys which are either task-specific or concentrate only on one type of visual content, i.e., image or video. Furthermore, we also provide some potential future directions in this field of research with an anticipation that this survey stimulates innovative thoughts and ideas to address the existing challenges and build new applications.

Deep Neural Networks (DNNs) have emerged as the core enabler of many major applications on mobile devices. To achieve high accuracy, DNN models have become increasingly deep with hundreds or even thousands of operator layers, leading to high memory and computational requirements for inference. Operator fusion (or kernel/layer fusion) is key optimization in many state-of-the-art DNN execution frameworks, such as TensorFlow, TVM, and MNN. However, these frameworks usually adopt fusion approaches based on certain patterns that are too restrictive to cover the diversity of operators and layer connections. Polyhedral-based loop fusion techniques, on the other hand, work on a low-level view of the computation without operator-level information, and can also miss potential fusion opportunities. To address this challenge, this paper proposes a novel and extensive loop fusion framework called DNNFusion. The basic idea of this work is to work at an operator view of DNNs, but expand fusion opportunities by developing a classification of both individual operators and their combinations. In addition, DNNFusion includes 1) a novel mathematical-property-based graph rewriting framework to reduce evaluation costs and facilitate subsequent operator fusion, 2) an integrated fusion plan generation that leverages the high-level analysis and accurate light-weight profiling, and 3) additional optimizations during fusion code generation. DNNFusion is extensively evaluated on 15 DNN models with varied types of tasks, model sizes, and layer counts. The evaluation results demonstrate that DNNFusion finds up to 8.8x higher fusion opportunities, outperforms four state-of-the-art DNN execution frameworks with 9.3x speedup. The memory requirement reduction and speedups can enable the execution of many of the target models on mobile devices and even make them part of a real-time application.

Approximating complex probability densities is a core problem in modern statistics. In this paper, we introduce the concept of Variational Inference (VI), a popular method in machine learning that uses optimization techniques to estimate complex probability densities. This property allows VI to converge faster than classical methods, such as, Markov Chain Monte Carlo sampling. Conceptually, VI works by choosing a family of probability density functions and then finding the one closest to the actual probability density -- often using the Kullback-Leibler (KL) divergence as the optimization metric. We introduce the Evidence Lower Bound to tractably compute the approximated probability density and we review the ideas behind mean-field variational inference. Finally, we discuss the applications of VI to variational auto-encoders (VAE) and VAE-Generative Adversarial Network (VAE-GAN). With this paper, we aim to explain the concept of VI and assist in future research with this approach.

This is a rush transcript of "Fox News Sunday" on August 27, 2021. This copy may not be in its final form and may be updated. A drone strike takes out two high profile ISIS-K targets, as U.S. troops continue their evacuation mission with just 48 hours to go in Afghanistan. JOHN KIRBY, PENTAGON PRESS SECRETARY: They lost a planner and they lost a facilitator and that got one wounded. WALLACE (voice-over): But warnings the threat is far from over. JEN PSAKI, WHITE HOUSE PRESS SECRETARY: Our troops are still in danger, that continues to be the case every day that they are there. WALLACE: With the clock ticking down, what does it mean for the security of our troops and civilians looking to get out of harm's way? We'll ask White House national security advisor Jake Sullivan about the situation on the ground and the danger in the final days of the mission. MITCH MCCONNELL (R-KY), MINORITY LEADER: The Taliban should not be allowed to tell us how long we are there to get our personnel out. WALLACE: We'll get reaction from Senate Republican leader Mitch McConnell, who's calling on the president to extend the evacuation beyond Tuesday. We'll ask our Sunday panel about the latest test for the nation's schools. We begin with breaking news on two stories. But first, the next two days could be the most tense and dangerous for U.S. They are trying to evacuate some of the thousands of Americans and Afghan civilians while at the same time rolling up their own operation. Meanwhile, President Biden making good on his promise to retaliate for the deadly suicide bombing in Kabul, ordering a drone strike that killed two ISIS-K planners and wounded another -- as his advisors warn another attack the airport is likely before the U.S. completes its exit. In a moment, we'll discuss all this with the president's national security advisor, Jake Sullivan. We begin with FOX team coverage. David Spunt is at the White House, but first, Trey Yingst in Doha, Qatar, with the latest on the ongoing withdrawal -- Trey.

The "Artificial Intelligence Global Market Report 2021: COVID-19 Growth and Change to 2030" report has been added to ResearchAndMarkets.com's offering. This report provides strategists, marketers and senior management with the critical information they need to assess the global artificial intelligence market. This report focuses on the artificial intelligence market which is experiencing strong growth. The report gives a guide to the artificial intelligence market which will be shaping and changing our lives over the next ten years and beyond, including the markets response to the challenge of the global pandemic. The global artificial intelligence market is expected to grow from $40.17 billion in 2020 to $51.56 billion in 2021 at a compound annual growth rate (CAGR) of 28.4%.

Have you ever wondered what famous historical figures like Nefertiti and Cleopatra looked like in real life? Well, Bas Uterwijk might be able to show you a pretty good guess. The Dutch photographer and digital artist creates amazing AI portraits of famous historical figures using innovative neural network reconstructions. To create these portraits, Uterwijk uploads numerous references of the person's likeness to the AI applications. Then, he makes small adjustments to the program until he is satisfied with the result.

Several intelligent transportation systems focus on studying the various driver behaviors for numerous objectives. This includes the ability to analyze driver actions, sensitivity, distraction, and response time. As the data collection is one of the major concerns for learning and validating different driving situations, we present a driver behavior switching model validated by a low-cost data collection solution using smartphones. The proposed model is validated using a real dataset to predict the driver behavior in short duration periods. A literature survey on motion detection (specifically driving behavior detection using smartphones) is presented. Multiple Markov Switching Variable Auto-Regression (MSVAR) models are implemented to achieve a sophisticated fitting with the collected driver behavior data. This yields more accurate predictions not only for driver behavior but also for the entire driving situation. The performance of the presented models together with a suitable model selection criteria is also presented. The proposed driver behavior prediction framework can potentially be used in accident prediction and driver safety systems.

In education, open-ended quiz questions have become an important tool for assessing the knowledge of students. Yet, manually preparing such questions is a tedious task, and thus automatic question generation has been proposed as a possible alternative. So far, the vast majority of research has focused on generating the question text, relying on question answering datasets with readily picked answers, and the problem of how to come up with answer candidates in the first place has been largely ignored. Here, we aim to bridge this gap. In particular, we propose a model that can generate a specified number of answer candidates for a given passage of text, which can then be used by instructors to write questions manually or can be passed as an input to automatic answer-aware question generators. Our experiments show that our proposed answer candidate generation model outperforms several baselines.