Sports broadcasters are continuously seeking to make their live coverages of soccer matches more attractive. A recent innovation is the “highlight channel,” which shows the most interesting events from multiple matches played at the same time. However, switching between matches at the right time is challenging in fast-paced sports like soccer, where interesting situations often evolve as quickly as they disappear again. This paper presents the POGBA algorithm for automatically predicting highlights in soccer matches, which is an important task that has not yet been addressed. POGBA leverages spatio-temporal event streams collected during matches to predict the probability that a particular game state will lead to a goal. An empirical evaluation on a real-world dataset shows that POGBA outperforms the baseline algorithms in terms of both precision and recall.

Up, up and away: Dubai hopes to have a passenger-carrying drone regularly buzzing through the skyline of this futuristic city-state in July. The arrival of the Chinese-made EHang 184 -- which already has had its flying debut over Dubai's iconic, sail-shaped Burj al-Arab skyscraper hotel -- comes as the Emirati city also has partnered with other cutting-edge technology companies, including Hyperloop One. The question is whether the egg-shaped, four-legged craft will really take off as a transportation alternative in this car-clogged city already home to the world's longest driverless metro line. Mattar al-Tayer, the head of Dubai's Roads & Transportation Agency, announced plans to have the craft regularly flying at the World Government Summit. Before his remarks on Monday, most treated the four-legged, eight-propeller craft as just another curiosity at an event that views itself as a desert Davos.

At CES 2017, tech companies introduced the world to loads of gadgets that talk back, making this a big year for intelligent assistants. If this trend continues, it might someday be common to talk to smart cars, table lamps, refrigerators, and TVs, thanks to smart technologies such as Amazon's Alexa. Demonstrating this cutting-edge technology at a trade show is one thing, but actually deploying it in a business setting is another. This begs the question: Will these assistants be truly useful anytime soon or are they gimmicks that need to work out their bugs (like causing you to accidentally order expensive stuff) before they're ready for prime time? Ideally, we want intelligent assistants like Alexa or Siri to "just work," like the computer in Star Trek.

This paper proposes a generic classification system designed to detect security threats based on the behavior of malware samples. The system relies on statistical features computed from proxy log fields to train detectors using a database of malware samples. The behavior detectors serve as basic reusable building blocks of the multi-level detection architecture. The detectors identify malicious communication exploiting encrypted URL strings and domains generated by a Domain Generation Algorithm (DGA) which are frequently used in Command and Control (C&C), phishing, and click fraud. Surprisingly, very precise detectors can be built given only a limited amount of information extracted from a single proxy log. This way, the computational requirements of the detectors are kept low which allows for deployment on a wide range of security devices and without depending on traffic context such as DNS logs, Whois records, webpage content, etc. Results on several weeks of live traffic from 100+ companies having 350k+ hosts show correct detection with a precision exceeding 95% of malicious flows, 95% of malicious URLs and 90% of infected hosts. In addition, a comparison with a signature and rule-based solution shows that our system is able to detect significant amount of new threats.

It is often critical in real-world applications to: (i) perform inverse learning of the cost parameters of a multi-objective reward based on observed agent behavior; (ii) perform sensitivity analyses of policies to various parameter settings; and (iii) analyze and optimize policy performance as a function of policy parameters. When such problems have mixed discrete and continuous state and/or action spaces, this leads to parameterized hybrid MDPs (PHMDPs) that are often approximately solved via discretization, sampling, and/or local gradient methods (when optimization is involved). In this paper we combine two recent advances that allow for the first exact solution and optimization of PHMDPs. We first show how each of the aforementioned use cases can be formalized as PHMDPs, which can then be solved via an extension of symbolic dynamic programming (SDP) even when the solution is piecewise nonlinear. Secondly, we leverage recent advances in non-convex solvers such as dReal and dOp (that offer δ-optimality guarantees for nonlinear problems given a symbolic function) for non-convex global optimization in (i), (ii), and (iii) using SDP to derive symbolic solutions to each PHMDP formalization. We demonstrate the efficacy and scalability of our framework by calculating the first known exact solutions to complex nonlinear examples of each of the aforementioned use cases.

Collaborative filtering (CF) with implicit feedback is a successful method for recommending items to users, which does not require a knowledge of the items or users. CF methods can be mainly classified into two categories. One is point-wise regression based and the other is pair-wise ranking based, where the latter one only tries to find out the items that users prefer while ignores the items that users dislike, and usually gives out a better recommended item list. The performance of CF-based methods degrades significantly when the feedback information is sparse. To address the problem, many kinds of auxiliary information have been utilized such as users’ reviews on items, items’ content and description information, price, brands. In this paper we utilize a weighted recursive autoencoder (RAE) to extract useful features from several heterogeneous auxiliary information and tightly couple the weighted RAE with a pair-wise ranking based CF method. Analysis of the hyperparameters illustrates that auxiliary information from different sources is indeed able to benefit our model. Empirical experiments on six real world datasets show that our method outperforms other state-of-the-art methods.

Online health resources aimed at older adults can have a significant impact on patient-physician relationships and on health outcomes. High quality online resources that are delivered in an ethical, emotionally aligned way can increase trust and reduce negative health outcomes such as anxiety. In contrast, low quality or misaligned resources can lead to harmful consequences such as inappropriate use of health care services and poor health decision-making. This paper investigates mechanisms for ensuring both quality and alignment of online health resources and interventions. First, the recently proposed QUEST evaluation instrument is examined. QUEST assesses the quality of online health information along six validated dimensions (authorship, attribution, conflict of interest, currency, complementarity, tone). A decision tree classifier is learned that is able to predict one criteria of the QUEST tool, complementarity, with an F1-score of 0.9 on a manually annotated dataset of 50 articles giving advice about Alzheimer disease. A social-psychological theory of affective (emotional) alignment is then presented, and demonstrated to gauge older adults emotional interpretations of eight examples of health recommendation systems related to Alzheimer disease (online memory tests). The paper concludes with a synthesizing view and a vision for the future of this important societal challenge.

Analysis of an organization's computer network activity is a key component of early detection and mitigation of insider threat, a growing concern for many organizations. Raw system logs are a prototypical example of streaming data that can quickly scale beyond the cognitive power of a human analyst. As a prospective filter for the human analyst, we present an online unsupervised deep learning approach to detect anomalous network activity from system logs in real time. Our models decompose anomaly scores into the contributions of individual user behavior features for increased interpretability to aid analysts reviewing potential cases of insider threat. Using the CERT Insider Threat Dataset v6.2 and threat detection recall as our performance metric, our novel deep and recurrent neural network models outperform Principal Component Analysis, Support Vector Machine and Isolation Forest based anomaly detection baselines. For our best model, the events labeled as insider threat activity in our dataset had an average anomaly score in the 95.53 percentile, demonstrating our approach's potential to greatly reduce analyst workloads.

Finding the music of the moment can often be a challenging problem, even for humans with well-versed musical tastes. These challenges further explode into a myriad of complexities when attempting to construct algorithmic approaches for automatic playlist generation. A variety of factors play a role in influencing a listener's perception of what music is appropriate on a given seed (e.g. Erik Schmidt, Senior Scientist at Pandora will be presenting at the Machine Intelligence Summit in San Francisco, 23-24 March. Erik will present an overview of recommendations at Pandora, followed by a deep dive into the challenges of recommending content.

Dear colleagues: Advances in Artificial Intelligence (AI) technology have opened up new markets and new opportunities for progress in critical areas such as health, education, energy, and the environment. In recent years, machines have surpassed humans in the performance of certain specific tasks, such as some aspects of image recognition. Experts forecast that rapid progress in the field of specialized artificial intelligence will continue. Although it is very unlikely that machines will exhibit broadly-applicable intelligence comparable to or exceeding that of humans in the next 20 years, it is to be expected that machines will reach and exceed human performance on more and more tasks. As a contribution toward preparing the United States for a future in which AI plays a growing role, this report surveys the current state of AI, its existing and potential applications, and the questions that are raised for society and public policy by progress in AI. The report also makes recommendations for specific further actions by Federal agencies and other actors. A companion document lays out a strategic plan for Federally-funded research and development in AI. Additionally, in the coming months, the Administration will release a follow-on report exploring in greater depth the effect of AI-driven automation on jobs and the economy.