We consider the problem faced by a recommender system which seeks to offer a user with unknown preferences an item. Before making a recommendation, the system has the opportunity to elicit the user's preferences by making queries. Each query corresponds to a pairwise comparison between items. We take the point of view of either a risk averse or regret averse recommender system which only possess set-based information on the user utility function. We investigate: a) an offline elicitation setting, where all queries are made at once, and b) an online elicitation setting, where queries are selected sequentially over time. We propose exact robust optimization formulations of these problems which integrate the elicitation and recommendation phases and study the complexity of these problems. For the offline case, where the problem takes the form of a two-stage robust optimization problem with decision-dependent information discovery, we provide an enumeration-based algorithm and also an equivalent reformulation in the form of a mixed-binary linear program which we solve via column-and-constraint generation. For the online setting, where the problem takes the form of a multi-stage robust optimization problem with decision-dependent information discovery, we propose a conservative solution approach. We evaluate the performance of our methods on both synthetic data and real data from the Homeless Management Information System. We simulate elicitation of the preferences of policy-makers in terms of characteristics of housing allocation policies to better match individuals experiencing homelessness to scarce housing resources. Our framework is shown to outperform the state-of-the-art techniques from the literature.

Time series classification using novel techniques has experienced a recent resurgence and growing interest from statisticians, subject-domain scientists, and decision makers in business and industry. This is primarily due to the ever increasing amount of big and complex data produced as a result of technological advances. A motivating example is that of Google trends data, which exhibit highly nonlinear behavior. Although a rich literature exists for addressing this problem, existing approaches mostly rely on first and second order properties of the time series, since they typically assume linearity of the underlying process. Often, these are inadequate for effective classification of nonlinear time series data such as Google Trends data. Given these methodological deficiencies and the abundance of nonlinear time series that persist among real-world phenomena, we introduce an approach that merges higher order spectral analysis (HOSA) with deep convolutional neural networks (CNNs) for classifying time series. The effectiveness of our approach is illustrated using simulated data and two motivating industry examples that involve Google trends data and electronic device energy consumption data.

Recent studies have shown that modern deep neural network classifiers are easy to fool, assuming that an adversary is able to slightly modify their inputs. Many papers have proposed adversarial attacks, defenses and methods to measure robustness to such adversarial perturbations. However, most commonly considered adversarial examples are based on $\ell_p$-bounded perturbations in the input space of the neural network, which are unlikely to arise naturally. Recently, especially in computer vision, researchers discovered "natural" or "semantic" perturbations, such as rotations, changes of brightness, or more high-level changes, but these perturbations have not yet been systematically utilized to measure the performance of classifiers. In this paper, we propose several metrics to measure robustness of classifiers to natural adversarial examples, and methods to evaluate them. These metrics, called latent space performance metrics, are based on the ability of generative models to capture probability distributions, and are defined in their latent spaces. On three image classification case studies, we evaluate the proposed metrics for several classifiers, including ones trained in conventional and robust ways. We find that the latent counterparts of adversarial robustness are associated with the accuracy of the classifier rather than its conventional adversarial robustness, but the latter is still reflected on the properties of found latent perturbations. In addition, our novel method of finding latent adversarial perturbations demonstrates that these perturbations are often perceptually small.

Machine learning lies at the heart of new possibilities for scientific discovery, knowledge generation, and artificial intelligence. Its potential benefits to these fields requires going beyond predictive accuracy and focusing on interpretability. In particular, many scientific problems require interpretations in a domain-specific interpretable feature space (e.g. the frequency domain) whereas attributions to the raw features (e.g. the pixel space) may be unintelligible or even misleading. To address this challenge, we propose TRIM (TRansformation IMportance), a novel approach which attributes importances to features in a transformed space and can be applied post-hoc to a fully trained model. TRIM is motivated by a cosmological parameter estimation problem using deep neural networks (DNNs) on simulated data, but it is generally applicable across domains/models and can be combined with any local interpretation method. In our cosmology example, combining TRIM with contextual decomposition shows promising results for identifying which frequencies a DNN uses, helping cosmologists to understand and validate that the model learns appropriate physical features rather than simulation artifacts.

In this paper we provide a comprehensive introduction to knowledge graphs, which have recently garnered significant attention from both industry and academia in scenarios that require exploiting diverse, dynamic, large-scale collections of data. After a general introduction, we motivate and contrast various graph-based data models and query languages that are used for knowledge graphs. We discuss the roles of schema, identity, and context in knowledge graphs. We explain how knowledge can be represented and extracted using a combination of deductive and inductive techniques. We summarise methods for the creation, enrichment, quality assessment, refinement, and publication of knowledge graphs. We provide an overview of prominent open knowledge graphs and enterprise knowledge graphs, their applications, and how they use the aforementioned techniques. We conclude with high-level future research directions for knowledge graphs.

After years of development, machine learning methods have matured enough to be used in clinical medicine. In 2018 the FDA approved software to screen patients for diabetic retinopathy, and the methods are rapidly making their way into other applications for image analysis, natural language processing, EHR data mining, drug discovery, and more. JAMA is proud to be a primary forum for the work of interdisciplinary groups demonstrating the use of machine learning methods for clinical medicine and health care. To understand the work read JAMA's Users' Guide to the Medical Literature How to Read Articles That Use Machine Learning, authored by Google Health scientists, and an accompanying commentary. See also JAMA Network's Health Informatics collection.

MARSEILLE, France--(BUSINESS WIRE)--Traxens, a company that provides high-value data and services for the supply chain industry, announces today that it is now part of the new European DataPorts project, aimed at creating a data platform for cognitive ports of the future. With a total budget of €6.7M ($7.3M), the three-year project will receive €5.7M ($6.2M) from the European Union. It is coordinated by the Technological Institute of Informatics (ITI) in Spain. Today, only three per cent of container terminals are automated. However, the future of the industry points towards smart ports as the best way to overcome the challenges and demands that arise in the sector.

While this ban on technically manipulated videos of political figures isn't new and has been in place since the last presidential election in 2016, it illustrates just how increasingly difficult it is for the public (and organisations) to verify a person's true identity online. A deepfake today uses AI to combine existing imagery to replicate both their face and voice. Essentially, they can impersonate a real person, making them appear to say words they have never even spoken – hence the fear when it comes to general elections and politics being skewed by misinformed videos. Worryingly, the number of them online has doubled in less than a year, from 7,964 in December 2018 to more than 14,000 just nine months later. While the majority of these are porn-related, the problem isn't solely defined to this space.

Federal guidance on artificial intelligence needs additions to ensure the U.S. has a seat at the international table. The rapid proliferation of applications of artificial intelligence and machine learning--or AI, for short--coupled with the potential for significant societal impact has spurred calls around the world for new regulation. The European Union and China are developing their own rules, and the Organization for Economic Cooperation and Development has developed principles that enjoy the support of its members plus a handful of other countries. In January, the U.S. Office of Management and Budget (OMB) also issued its own draft guidance, ensuring the United States a seat at the table during this ongoing, multi-year, international conversation. The U.S. guidance--covering "weak" or narrow AI applications of the kind we experience today--reflects a light-touch approach to regulation, consistent with a desire to reward U.S. ingenuity.

Elon Musk believes the era of fighter jets is over and future warfare will be carried out by autonomous drones. The Tesla and SpaceX CEO made the prediction while speaking with US Air Force Lt. Gen. John Thompson at the Air Warfare Symposium in Orlando, Florida on Friday. 'Drone warfare is where the future will be. It's not that I want the future to be – it's just, this is what the future will be,' the billionaire said. Musk also believes that Lockheed Martin's F-35 fighter jet, is the Pentagon's most expensive weapons system, should have a competitor – and specifically a'drone fighter plane', according to CNBC.