In this paper, we present a cost-based approach for the automatic selection and allocation of a disjoint ensemble of black-box predictors to answer predictive spatio-temporal queries. Our approach is divided into two parts -- offline and online. During the offline part, we preprocess the predictive domain data -- transforming it into a regular grid -- and the black-box models -- computing their spatio-temporal learning function. In the online part, we compute a DJEnsemble plan which minimizes a multivariate cost function based on estimates for the prediction error and the execution cost -- producing a model spatial allocation matrix -- and run the optimal ensemble plan. We conduct a set of extensive experiments that evaluate the DJEnsemble approach and highlight its efficiency. We show that our cost model produces plans with performance close to the actual best plan. When compared against the traditional ensemble approach, DJEnsemble achieves up to $4X$ improvement in execution time and almost $9X$ improvement in prediction accuracy. To the best of our knowledge, this is the first work to solve the problem of optimizing the allocation of black-box models to answer predictive spatio-temporal queries.

Will self-driving cars be able to cope with highly dangerous roads? Let's talk about dangerous roads. In a moment, I'll provide you with a recently published list of the presumed Top Ten most dangerous roads in the world. For some of you, the odds are that you'll be happy that you've never had a cause to try and traverse these bad-to-the-bone roads, while others of you are probably going to put these alarming roads on your bucket list of places you have to go and give a whirl someday. Do you prefer roads that are calm, easy to navigate, and present little or no qualms?

From public CCTV cameras to biometric identification systems in airports, facial recognition technology is now common in a growing number of places around the world. In its most benign form, facial recognition technology is a convenient way to unlock your smartphone. At the state level though, facial recognition is a key component of mass surveillance, and it already touches half the global population on a regular basis. Today's visualizations from SurfShark classify 194 countries and regions based on the extent of surveillance. Click here to explore the full research methodology.

Delaying the reopening of primary schools in England on 1 June by two weeks could halve the risk to each child of being exposed to an infectious classmate, according to a report by the Independent Scientific Advisory Group for Emergencies, a recently-formed group of scientists that is seeking to provide alternative advice to the UK government. The group say that modelling suggests that waiting until September would reduce this risk further, to less than the risk to children of road traffic accidents. The group is chaired by former government chief scientific advisor David King and is separate from the official SAGE committee that advises the UK government. "The crucial factor allowing school reopening around the world has been the presence of well-functioning local test, trace and isolate protocols – something that is now accepted will not be in place in England by early June," the report says. It adds that before schools can reopen, it is important to confirm that daily new ...

Ceibal Foundation is organizing the 3rd edition of the EdTech Winter School in partnership with ANII (Agencia Nacional de Investigación e Innovación) and with the support of the International Development Research Centre -IDRC-. The EdTech Winter School is a multi-stakeholder initiative organized within the framework of the Education Sector Fund "Digital Inclusion: Education with New Horizons" created with ANII and ADELA (Alliance for the Digitalization of Education in Latin America) supported by the International Development Research Centre (IDRC). In this context and for the past three years, the Winter School focused in creating a stimulating learning environment to present and discuss key challenges, research trends and opportunities; to foresee new horizons in education, learning and teaching practices enhanced by digital technologies. This year's edition "Human Centered Technologies for Education" aims to assess, analyze and explore the changes, opportunities and challenges that technology-driven transformations are creating for education worldwide. Advances in areas as automation, artificial intelligence, robotics, Big Data, among others, are shaping society in ways that could not be foreseen a few years ago.

The NHS Confederation, a membership body that represents people who commission or provide NHS services, has warned of the urgent need for a UK contact tracing strategy. "Our members are concerned that unless there is a clear strategy, then there must be a greater risk of a second wave of infections and serious health consequences," chief executive Niall Dickson wrote in a letter sent to the UK's health and social care minister Matt Hancock yesterday. "We would therefore urge you to produce such a strategy with a clear implementation plan ahead of any further easing of the lockdown." Dickson welcomed Prime Minister Boris Johnson's new commitment to trace 10,000 new coronavirus cases per day by 1 June, adding that "delivery and implementation will be critical, and we await further details." However, he said that a strategy for tracing contacts "should have been in place much sooner". An international randomised controlled trial investigating whether hydroxychloroquine and chloroquine ...

The past several years have witnessed a huge surge in the use of social media platforms during mass convergence events such as health emergencies, natural or human-induced disasters. These non-traditional data sources are becoming vital for disease forecasts and surveillance when preparing for epidemic and pandemic outbreaks. In this paper, we present GeoCoV19, a large-scale Twitter dataset containing more than 524 million multilingual tweets posted over a period of 90 days since February 1, 2020. Moreover, we employ a gazetteer-based approach to infer the geolocation of tweets. We postulate that this large-scale, multilingual, geolocated social media data can empower the research communities to evaluate how societies are collectively coping with this unprecedented global crisis as well as to develop computational methods to address challenges such as identifying fake news, understanding communities' knowledge gaps, building disease forecast and surveillance models, among others.

In this paper, we provide an overview of the existing methods for integrating human advice into a Reinforcement Learning process. We propose a taxonomy of different types of teaching signals, and present them according to three main aspects: how they can be provided to the learning agent, how they can be integrated into the learning process, and how they can be interpreted by the agent if their meaning is not determined beforehand. Finally, we compare the benefits and limitations of using each type of teaching signals, and propose a unified view of interactive learning methods.

Hybrid variations of metaheuristics that include data mining strategies have been utilized to solve a variety of combinatorial optimization problems, with superior and encouraging results. Previous hybrid strategies applied mined patterns to guide the construction of initial solutions, leading to more effective exploration of the solution space. Solving a combinatorial optimization problem is usually a hard task because its solution space grows exponentially with its size. Therefore, problem size reduction is also a useful strategy in this context, especially in the case of large-scale problems. In this paper, we build upon these ideas by presenting an approach named MineReduce, which uses mined patterns to perform problem size reduction. We present an application of MineReduce to improve a heuristic for the heterogeneous fleet vehicle routing problem. The results obtained in computational experiments show that this proposed heuristic demonstrates superior performance compared to the original heuristic and other state-of-the-art heuristics, achieving better solution costs with shorter run times.

This paper presents a novel attention-based algorithm for achieving adaptive computation called DACT, which, unlike existing ones, is end-to-end differentiable. Our method can be used in conjunction with many networks; in particular, we study its application to the widely known MAC architecture, obtaining a significant reduction in the number of recurrent steps needed to achieve similar accuracies, therefore improving its performance to computation ratio. Furthermore, we show that by increasing the maximum number of steps used, we surpass the accuracy of even our best non-adaptive MAC in the CLEVR dataset, demonstrating that our approach is able to control the number of steps without significant loss of performance. Additional advantages provided by our approach include considerably improving interpretability by discarding useless steps and providing more insights into the underlying reasoning process. Finally, we present adaptive computation as an equivalent to an ensemble of models, similar to a mixture of expert formulation. Both the code and the configuration files for our experiments are made available to support further research in this area.