A company called Waverly Labs is working on a wearable translation device that has captured people's imaginations, generated plenty of buzz, andraised over 3 million on Indiegogo. That two people wearing earpieces made by the company could speak in different languages, and with the earpieces working in conjunction with a smartphone app, each person could hear a translation in their preferred language in their ear. For example, one person could speak Spanish, and the other would hear it as English in his ear, and vice versa. The idea is undoubtedly exciting to anyone who has felt the limits of a language barrier. And a video that the company posted that demonstrates the device in action, translating between English and French, has been viewed over 280,000 times.

The number of methods available for classification of multi-label data has increased rapidly over recent years, yet relatively few links have been made with the related task of classification of sequential data. If labels indices are considered as time indices, the problems can often be seen as equivalent. In this paper we detect and elaborate on connections between multi-label methods and Markovian models, and study the suitability of multi-label methods for prediction in sequential data. From this study we draw upon the most suitable techniques from the area and develop two novel competitive approaches which can be applied to either kind of data. We carry out an empirical evaluation investigating performance on real-world sequential-prediction tasks: electricity demand, and route prediction. As well as showing that several popular multi-label algorithms are in fact easily applicable to sequencing tasks, our novel approaches, which benefit from a unified view of these areas, prove very competitive against established methods. Keywords: multi-label classification; problem transformation; sequential data; sequence prediction; Markov models 1. Introduction Multi-label classification is the supervised learning problem where an instance is associated with multiple class variables (i.e., labels), rather than with a single class, as in traditional classification problems. See [1] for a review. Corresponding author, jesse.read@polytechnique.edu Preprint submitted to Pattern Recognition September 29, 2016 labels were modelled independently - at the expense of an increased computational cost. The case of binary labels is most common, where a positive class value denotes the relevance of the label (and the negative or null class denotes irrelevance). Typical examples of binary multi-label classification involve categorizing text documents and images, which can be assigned any subset of a particular label set. For example, an image can be associated with both labels beach and sunset. The multi-label classification paradigm has been successfully considered also in many other domains, such as text, video, audio, and bioinformatics - see [1] and references therein for further examples.

The empirical validation of community detection methods is often based on available annotations on the nodes that serve as putative indicators of the large-scale network structure. Most often, the suitability of the annotations as topological descriptors itself is not assessed, and without this it is not possible to ultimately distinguish between actual shortcomings of the community detection algorithms on one hand, and the incompleteness, inaccuracy or structured nature of the data annotations themselves on the other. In this work we present a principled method to access both aspects simultaneously. We construct a joint generative model for the data and metadata, and a nonparametric Bayesian framework to infer its parameters from annotated datasets. We assess the quality of the metadata not according to its direct alignment with the network communities, but rather in its capacity to predict the placement of edges in the network. We also show how this feature can be used to predict the connections to missing nodes when only the metadata is available, as well as missing metadata. By investigating a wide range of datasets, we show that while there are seldom exact agreements between metadata tokens and the inferred data groups, the metadata is often informative of the network structure nevertheless, and can improve the prediction of missing nodes. This shows that the method uncovers meaningful patterns in both the data and metadata, without requiring or expecting a perfect agreement between the two.

Gaussian graphical models are widely utilized to infer and visualize networks of dependencies between continuous variables. However, inferring the graph is difficult when the sample size is small compared to the number of variables. To reduce the number of parameters to estimate in the model, we propose a non-asymptotic model selection procedure supported by strong theoretical guarantees based on an oracle type inequality and a minimax lower bound. The covariance matrix of the model is approximated by a block-diagonal matrix. The structure of this matrix is detected by thresholding the sample covariance matrix, where the threshold is selected using the slope heuristic. Based on the block-diagonal structure of the covariance matrix, the estimation problem is divided into several independent problems: subsequently, the network of dependencies between variables is inferred using the graphical lasso algorithm in each block. The performance of the procedure is illustrated on simulated data. An application to a real gene expression dataset with a limited sample size is also presented: the dimension reduction allows attention to be objectively focused on interactions among smaller subsets of genes, leading to a more parsimonious and interpretable modular network. Contents 1. Introduction 2 2. A method to detect block-diagonal covariance structure 3 3. Theoretical results for non-asymptotic model selection 5 4. Simulation study 8 4.1.

A 23-year-old employee of the city of Ota, Gunma Prefecture, lied that he had won an overseas video game contest, leading to false reports about his victory in two Japanese newspapers, it has been learned. On Wednesday, the major daily Asahi Shimbun and Jomo Shimbun, the regional newspaper distributed in Gunma, issued an apology and retracted their stories about the man, who has admitted that a detailed account of his win at a French gaming competition was all fiction. The man, who is a temporary employee of the Ota Municipal Government, even held a news conference at City Hall on Monday, saying he won the tournament for players of "Guilty Gear," a PlayStation game, held on Sept. 20-21 in Paris. He even cited the name of the tournament, saying he had been invited to the event based on his past records as an amateur player. The Asahi and Jomo both carried articles on the man with a picture of him holding a game console at the news conference.

Just a few weeks ago, we posted about some incredible research from Vijay Kumar's lab at the University of Pennsylvania getting quadrotors to zip through narrow gaps using only onboard localization. This is a big deal, because it means that drones are getting closer to being able to aggressively avoid obstacles without depending on external localization systems. The one little asterisk to this research was that the quadrotors were provided the location and orientation of the gap in advance, rather than having to figure it out for themselves. Yesterday, Davide Falanga, Elias Mueggler, Matthias Faessler, and Professor Davide Scaramuzza, who leads the Robotics and Perception Group at the University of Zurich, shared some research that they've just submitted to ICRA 2017. It's the same kind of aggressive quadrotor maneuvering, except absolutely everything is done on board, including obstacle perception.

Google, Facebook, Amazon, IBM and Microsoft are joining forces to create a new AI partnership dedicated to advancing public understanding of the sector, as well as coming up with standards for future researchers to abide by. Going by the unwieldy name of the Partnership on Artificial Intelligence to Benefit People and Society, the alliance isn't a lobbying organisation (at least, it says it "does not intend" to lobby government bodies). Instead, it says it will "conduct research, recommend best practices, and publish research under an open license in areas such as ethics, fairness and inclusivity; transparency, privacy, and interoperability; collaboration between people and AI systems; and the trustworthiness, reliability and robustness of the technology". There will be equal representation between corporate and non-corporate members on the board of the partnership, and it hopes to invite "academics, non-profits and specialists in policy and ethics" to join. Each of the five founding corporate members has strong AI research teams, some of which have become household names, such as IBM's Watson and Amazon's Alexa.

Alison Carnwath, chairman of one of the UK's largest construction firms says the Era of Robots is at hand. Don't miss Zume Pizza Robots, Uber's Security Robots, Local Delivery Robots Invade London Thousands of builders will lose jobs as machines take over building London skyscrapers. Skyscrapers in the City of London could soon be built by robots rather than by people, according to the boss of one of the UK's biggest construction firms. The result would be huge productivity gains as more work could be done by fewer people – but also mass layoffs as traditionally labour-intensive construction projects hire fewer and fewer staff. "We're moving into the era of the robots," said Alison Carnwath, the chairman of Land Securities, the 8.2bn FTSE 100 construction company.

Initially based in Peru, Laboratoria has expanded into Mexico and Chile.

ARE your hidden biases soon to be revealed? A computer program can unmask them by scrutinising people's body language for signs of prejudice. Algorithms can already accurately read people's emotions from their facial expressions or speech patterns. So a team of researchers in Italy wondered if they could be used to uncover people's hidden racial biases. First, they asked 32 white college students to fill out two questionnaires. One was designed to suss out their explicit biases, while the second, an Implicit Association Test, aimed to uncover their subconscious racial biases.