Coalition formation typically involves the coming together of multiple, heterogeneous, agents to achieve both their individual and collective goals. In this paper, we focus on a special case of coalition formation known as Graph-Constrained Coalition Formation (GCCF) whereby a network connecting the agents constrains the formation of coalitions. We focus on this type of problem given that in many real-world applications, agents may be connected by a communication network or only trust certain peers in their social network. We propose a novel representation of this problem based on the concept of edge contraction, which allows us to model the search space induced by the GCCF problem as a rooted tree. Then, we propose an anytime solution algorithm (CFSS), which is particularly efficient when applied to a general class of characteristic functions called $m+a$ functions. Moreover, we show how CFSS can be efficiently parallelised to solve GCCF using a non-redundant partition of the search space. We benchmark CFSS on both synthetic and realistic scenarios, using a real-world dataset consisting of the energy consumption of a large number of households in the UK. Our results show that, in the best case, the serial version of CFSS is 4 orders of magnitude faster than the state of the art, while the parallel version is 9.44 times faster than the serial version on a 12-core machine. Moreover, CFSS is the first approach to provide anytime approximate solutions with quality guarantees for very large systems of agents (i.e., with more than 2700 agents).

Despite the growing importance of multilingual aspect of web search, no appropriate offline metrics to evaluate its quality are proposed so far. At the same time, personal language preferences can be regarded as intents of a query. This approach translates the multilingual search problem into a particular task of search diversification. Furthermore, the standard intent-aware approach could be adopted to build a diversified metric for multilingual search on the basis of a classical IR metric such as ERR. The intent-aware approach estimates user satisfaction under a user behavior model. We show however that the underlying user behavior models is not realistic in the multilingual case, and the produced intent-aware metric do not appropriately estimate the user satisfaction. We develop a novel approach to build intent-aware user behavior models, which overcome these limitations and convert to quality metrics that better correlate with standard online metrics of user satisfaction.

Reinforcement learning is considered to be a strong AI paradigm which can be used to teach machines through interaction with the environment and learning from their mistakes, but it has not yet been successfully used for automotive applications. There has recently been a revival of interest in the topic, however, driven by the ability of deep learning algorithms to learn good representations of the environment. Motivated by Google DeepMind's successful demonstrations of learning for games from Breakout to Go, we will propose different methods for autonomous driving using deep reinforcement learning. This is of particular interest as it is difficult to pose autonomous driving as a supervised learning problem as it has a strong interaction with the environment including other vehicles, pedestrians and roadworks. As this is a relatively new area of research for autonomous driving, we will formulate two main categories of algorithms: 1) Discrete actions category, and 2) Continuous actions category. For the discrete actions category, we will deal with Deep Q-Network Algorithm (DQN) while for the continuous actions category, we will deal with Deep Deterministic Actor Critic Algorithm (DDAC). In addition to that, We will also discover the performance of these two categories on an open source car simulator for Racing called (TORCS) which stands for The Open Racing car Simulator. Our simulation results demonstrate learning of autonomous maneuvering in a scenario of complex road curvatures and simple interaction with other vehicles. Finally, we explain the effect of some restricted conditions, put on the car during the learning phase, on the convergence time for finishing its learning phase.

Deep convolutional neural networks (CNNs) have shown great potential for numerous real-world machine learning applications, but performing inference in large CNNs in real-time remains a challenge. We have previously demonstrated that traditional CNNs can be converted into deep spiking neural networks (SNNs), which exhibit similar accuracy while reducing both latency and computational load as a consequence of their data-driven, event-based style of computing. Here we provide a novel theory that explains why this conversion is successful, and derive from it several new tools to convert a larger and more powerful class of deep networks into SNNs. We identify the main sources of approximation errors in previous conversion methods, and propose simple mechanisms to fix these issues. Furthermore, we develop spiking implementations of common CNN operations such as max-pooling, softmax, and batch-normalization, which allow almost loss-less conversion of arbitrary CNN architectures into the spiking domain. Empirical evaluation of different network architectures on the MNIST and CIFAR10 benchmarks leads to the best SNN results reported to date.

A company's logo is an important part of its identity, but the processes behind defining, registering, and protecting these trademarks is a convoluted and rather archaic one. A startup called TrademarkVision aims to simplify it by replacing that laborious and arcane process with what amounts to a machine-learning-powered reverse image search. This isn't in some lab, either: the EU just switched their whole image trademark system over to it. Most people probably haven't had to do many trademark and logo searches. Well, why don't you take the USPTO's version for a spin so you know what it's like? Try to find the Nike "Swoosh" or something.

Microsoft reveals'what if' face mashup system that can you show everything from Voldemort in Kiss to Donald Trump in Game of Thrones The chatbot has since taken the internet by storm, with users creating'what if' images for every imaginable situation. This includes'What if Trump is Cersei Lannister' proposed by Twitter user Jeremy Randall Pictured is a terrifying baby-Yoda mashup it created when asked'What if Yoda were BB-8?' The bot created an image to visualize'What if Chewbacca were Yoda?' There are often those moments in life that cause us to wonder, 'what if' – but, Microsoft's new chatbot might make you wish you never had. The new bot called'Murphy' generates mashup images for any hypothetical face combination, with hilarious, and often terrifying, results Twitter user Stephen Bell asked the bot, 'What if Voldemort was in Kiss?' Valley Stream Best Buy associates gift a teen with a Wii U'I'm going to wing walk!' Schofield talks to Duke about wing walk Prince Philip reminisces about expansion of Duke of Edinburgh awards Homeowner trolls bungling burglar with Mission Impossible theme'They make each other laugh': Countess Sophie on the Duke and Queen Hunters forced to shoot a wild bear dead as it charges towards them'I wanted the painting!': Joanna Lumley jokes about Duke's artwork Documentary director attacked by gang of immigrants in Stockholm Adorable baby dressed as Lion comes face to face with real one Hammer wielding thugs smash car windows and threaten man Adorable dog won't allow owner to stop scratching his belly Ferrari crashes into pedestrians while racing near Battersea Dogs Home Adorable dog won't allow owner to stop scratching his belly Terminally-ill boy, five, dies in Santa Claus' arms after... Missing North Carolina girl who was last seen aged 15... Trump's Iran stance could threaten a WORLD WAR and the... Woman left with huge bill after Plenty of Fish date eats... Model, 32, claims her MIT-grad hedge-funder boyfriend, 29,... Blood-spattered walls, unbearable odours and houses where... Best Buy employees in Long Island chip in to buy a $300 WiiU... Nothing like retail therapy!

The corpus is intended to serve as a reference for training and evaluating methods for anatomical entity mention detection in life science publications.

In May of 2012, a car and a truck dove along highway in Spain. The one thing they were missing? The convoy drove 120 miles without human intervention during the experiment in which Sarte project – driven ahead by European Commission – aims to develop autonomous road trains to lead these convoys and reduce traffic, accidents and improve flow. This was a small milestone in a year that saw large leaps in the field of self-driving cars. Google's self-driven vehicles have famously gone 30,000 miles without an accident or incident, and are now licensed in both Nevada and California for road use.

Numer.ai is a crowdsourced hedge fund for machine learning experts Richard Craib believes that some of the best stock pickers aren't on Wall Street. The former hedge funder came to the realization that tech's machine learning experts may be able to build better predictive models than those with finance backgrounds. Craib carried this thesis forward when he launched Numer.ai last year, a crowdsourced hedge fund. The startup hopes to attract the best and brightest minds at companies like Google and pay them for their AI skills. And the first year saw significant traction, with 7500 "data scientists" creating algorithms on Numer.ai's Now the startup is announcing $6 million in funding from First Round Capital and Union Square Ventures to continue their team's expansion and buy more historical data sets (Craib refused to say where they get their data from).

Apple will allow its artificial intelligence teams to publish research papers for the first time, marking a significant change in strategy that could help accelerate the iPhone maker's advances in deep learning. When Apple introduced its Siri virtual assistant in 2011, the company appeared to have a head start over many of its nearest competitors. But it has lost ground since then to the likes of Alphabet Inc.'s Google Assistant and Amazon.com Researchers say among the reasons Apple has failed to keep pace is its unwillingness to allow its AI engineers to publish scientific papers, stymieing its ability to feed off wider advances in the field. That policy has now changed, Russ Salakhutdinov, an Apple director of AI research, said last week at the Neural Information Processing Systems conference in Barcelona, Spain, according to Twitter posts from those present.