A growing number of universities worldwide use various forms of online and blended learning as part of their academic curricula. Furthermore, the recent changes caused by the COVID-19 pandemic have led to a drastic increase in importance and ubiquity of online education. Among the major advantages of e-learning is not only improving students' learning experience and widening their educational prospects, but also an opportunity to gain insights into students' learning processes with learning analytics. This study contributes to the topic of improving and understanding e-learning processes in the following ways. First, we demonstrate that accurate predictive models can be built based on sequential patterns derived from students' behavioral data, which are able to identify underperforming students early in the course. Second, we investigate the specificity-generalizability trade-off in building such predictive models by investigating whether predictive models should be built for every course individually based on course-specific sequential patterns, or across several courses based on more general behavioral patterns. Finally, we present a methodology for capturing temporal aspects in behavioral data and analyze its influence on the predictive performance of the models. The results of our improved sequence classification technique are capable to predict student performance with high levels of accuracy, reaching 90 percent for course-specific models.

Ariel Koren, a Google employee who became a face of worker protests against the company's contract with the Israeli government, announced her resignation yesterday. The Jewish marketing manager says she faced retaliation from management and some colleagues for expressing pro-Palestinian views within the company. In October she joined other Google and Amazon employees in public opposition to Project Nimbus, a $1.2 billion contract for Google and Amazon to provide cloud computing to Israel, including its defense ministry. She says that Google later gave her an ultimatum: Agree to move to Brazil within 17 days or lose her job. Training documents leaked to the Intercept show Project Nimbus providing Israel with access to Google's cloud AI services, including face and expression detection, video analysis, and sentiment analysis.

Netflix is pioneering content creation at an unprecedented scale. Our catalog of thousands of films and series caters to 195M members in over 190 countries who span a broad and diverse range of tastes. Content, marketing, and studio production executives make the key decisions that aspire to maximize each series' or film's potential to bring joy to our subscribers as it progresses from pitch to play on our service. Our job is to support them. The commissioning of a series or film, which we refer to as a title, is a creative decision. Executives consider many factors including narrative quality, relation to the current societal context or zeitgeist, creative talent relationships, and audience composition and size, to name a few.

Machine learning offers an exciting opportunity to improve the calibration of nearly all reconstructed objects in high-energy physics detectors. However, machine learning approaches often depend on the spectra of examples used during training, an issue known as prior dependence. This is an undesirable property of a calibration, which needs to be applicable in a variety of environments. The purpose of this paper is to explicitly highlight the prior dependence of some machine learning-based calibration strategies. We demonstrate how some recent proposals for both simulation-based and data-based calibrations inherit properties of the sample used for training, which can result in biases for downstream analyses. In the case of simulation-based calibration, we argue that our recently proposed Gaussian Ansatz approach can avoid some of the pitfalls of prior dependence, whereas prior-independent data-based calibration remains an open problem.

Kernel-based tests provide a simple yet effective framework that use the theory of reproducing kernel Hilbert spaces to design non-parametric testing procedures. In this paper we propose new theoretical tools that can be used to study the asymptotic behaviour of kernel-based tests in several data scenarios, and in many different testing problems. Unlike current approaches, our methods avoid using lengthy $U$ and $V$ statistics expansions and limit theorems, that commonly appear in the literature, and works directly with random functionals on Hilbert spaces. Therefore, our framework leads to a much simpler and clean analysis of kernel tests, only requiring mild regularity conditions. Furthermore, we show that, in general, our analysis cannot be improved by proving that the regularity conditions required by our methods are both sufficient and necessary. To illustrate the effectiveness of our approach we present a new kernel-test for the conditional independence testing problem, as well as new analyses for already known kernel-based tests.

Prediction of individual's race and ethnicity plays an important role in social science and public health research. Examples include studies of racial disparity in health and voting. Recently, Bayesian Improved Surname Geocoding (BISG), which uses Bayes' rule to combine information from Census surname files with the geocoding of an individual's residence, has emerged as a leading methodology for this prediction task. Unfortunately, BISG suffers from two Census data problems that contribute to unsatisfactory predictive performance for minorities. First, the decennial Census often contains zero counts for minority racial groups in the Census blocks where some members of those groups reside. Second, because the Census surname files only include frequent names, many surnames -- especially those of minorities -- are missing from the list. To address the zero counts problem, we introduce a fully Bayesian Improved Surname Geocoding (fBISG) methodology that accounts for potential measurement error in Census counts by extending the naive Bayesian inference of the BISG methodology to full posterior inference. To address the missing surname problem, we supplement the Census surname data with additional data on last, first, and middle names taken from the voter files of six Southern states where self-reported race is available. Our empirical validation shows that the fBISG methodology and name supplements significantly improve the accuracy of race imputation across all racial groups, and especially for Asians. The proposed methodology, together with additional name data, is available via the open-source software WRU.

The Mohajer-6 has the capability to carry out surveillance and reconnaissance missions, and the Shahed series is considered among the most capable of Iran's military drones, according to comments made by the Iranian military to local news media. Iran is a pioneer in drone technology, with at least four decades of design and manufacturing experience, and it has been providing combat drones to military groups and proxy militia in Yemen, Iraq, Syria, Lebanon and Gaza. Officials in Israel, the United States and some Sunni Arab countries like Saudi Arabia have said they are increasingly concerned that Iran's advancing drone technology could destabilize the region and empower militias backed by Iran. In the shadow war between Iran and Israel, Iranian drones have been involved in attacks on ships and have targeted U.S. military bases in Iraq and Syria. Israel has also attacked a secret facility in western Iran where hundreds of drones were believed to have been stored.

The quantification of fat depots on the surroundings of the heart is an accurate procedure for evaluating health risk factors correlated with several diseases. However, this type of evaluation is not widely employed in clinical practice due to the required human workload. This work proposes a novel technique for the automatic segmentation of cardiac fat pads. The technique is based on applying classification algorithms to the segmentation of cardiac CT images. Furthermore, we extensively evaluate the performance of several algorithms on this task and discuss which provided better predictive models. Experimental results have shown that the mean accuracy for the classification of epicardial and mediastinal fats has been 98.4% with a mean true positive rate of 96.2%. On average, the Dice similarity index, regarding the segmented patients and the ground truth, was equal to 96.8%. Therfore, our technique has achieved the most accurate results for the automatic segmentation of cardiac fats, to date.

We propose a methodology to predict the cardiac epicardial and mediastinal fat volumes in computed tomography images using regression algorithms. The obtained results indicate that it is feasible to predict these fats with a high degree of correlation, thus alleviating the requirement for manual or automatic segmentation of both fat volumes. Instead, segmenting just one of them suffices, while the volume of the other may be predicted fairly precisely. The correlation coefficient obtained by the Rotation Forest algorithm using MLP Regressor for predicting the mediastinal fat based on the epicardial fat was 0.9876, with a relative absolute error of 14.4% and a root relative squared error of 15.7%. The best correlation coefficient obtained in the prediction of the epicardial fat based on the mediastinal was 0.9683 with a relative absolute error of 19.6% and a relative squared error of 24.9%. Moreover, we analysed the feasibility of using linear regressors, which provide an intuitive interpretation of the underlying approximations. In this case, the obtained correlation coefficient was 0.9534 for predicting the mediastinal fat based on the epicardial, with a relative absolute error of 31.6% and a root relative squared error of 30.1%. On the prediction of the epicardial fat based on the mediastinal fat, the correlation coefficient was 0.8531, with a relative absolute error of 50.43% and a root relative squared error of 52.06%. In summary, it is possible to speed up general medical analyses and some segmentation and quantification methods that are currently employed in the state-of-the-art by using this prediction approach, which consequently reduces costs and therefore enables preventive treatments that may lead to a reduction of health problems.

A big convergence of language, vision, and multimodal pretraining is emerging. In this work, we introduce a general-purpose multimodal foundation model BEiT-3, which achieves state-of-the-art transfer performance on both vision and vision-language tasks. Specifically, we advance the big convergence from three aspects: backbone architecture, pretraining task, and model scaling up. We introduce Multiway Transformers for general-purpose modeling, where the modular architecture enables both deep fusion and modality-specific encoding. Based on the shared backbone, we perform masked "language" modeling on images (Imglish), texts (English), and image-text pairs ("parallel sentences") in a unified manner. Experimental results show that BEiT-3 obtains state-of-the-art performance on object detection (COCO), semantic segmentation (ADE20K), image classification (ImageNet), visual reasoning (NLVR2), visual question answering (VQAv2), image captioning (COCO), and cross-modal retrieval (Flickr30K, COCO).