We provide a distribution-free test that can be used to determine whether any two joint distributions $p$ and $q$ are statistically different by inspection of a large enough set of samples. Following recent efforts from Long et al. [1], we rely on joint kernel distribution embedding to extend the kernel two-sample test of Gretton et al. [2] to the case of joint probability distributions. Our main result can be directly applied to verify if a dataset-shift has occurred between training and test distributions in a learning framework, without further assuming the shift has occurred only in the input, in the target or in the conditional distribution.

Datalog+/- is a family of ontology languages that combine good computational properties with high expressive power. Datalog+/- languages are provably able to capture the most relevant Semantic Web languages. In this paper we consider the class of weakly-sticky (WS) Datalog+/- programs, which allow for certain useful forms of joins in rule bodies as well as extending the well-known class of weakly-acyclic TGDs. So far, only non-deterministic algorithms were known for answering queries on WS Datalog+/- programs. We present novel deterministic query answering algorithms under WS Datalog+/-. In particular, we propose: (1) a bottom-up grounding algorithm based on a query-driven chase, and (2) a hybrid approach based on transforming a WS program into a so-called sticky one, for which query rewriting techniques are known. We discuss how our algorithms can be optimized and effectively applied for query answering in real-world scenarios.

Nasa has announced that it has found evidence of flowing water on Mars. Scientists have long speculated that Recurring Slope Lineae -- or dark patches -- on Mars were made up of briny water but the new findings prove that those patches are caused by liquid water, which it has established by finding hydrated salts. Several hundred camped outside the London store in Covent Garden. The 6s will have new features like a vastly improved camera and a pressure-sensitive "3D Touch" display

Artificial intelligence and robotics have enjoyed a resurgence of interest, and there is renewed optimism about their place in our future. But what do they mean for us? You submitted your questions about artificial intelligence and robotics, and we put them – and some of our own – to The Conversation's experts. It is 100% plausible that we'll have human-like artificial intelligence. I say this even though the human brain is the most complex system in the universe that we know of. But there are also no physical laws we know of that would prevent us reproducing or exceeding its capabilities. Popular AI from Issac Asimov to Steven Spielberg is plausible. What the question doesn't address is: when will it be plausible?

Elon Musk's new master plan to produce a fleet of fully self-driving vehicles and autonomous technology flies in the face of the techno-luminary's self-described fear of a robot takeover. Musk's grand plan to merge solar panel producer SolarCity and Tesla includes producing a giant, self-controlled machine that builds the machines that the electric vehicle maker produces -- in effect, the plan is to turn Tesla's factories into a product themselves. The so-called master plan, which was announced Wednesday in a blog post on the Tesla website, involves creating fully autonomous technology, which will allow customers to let their computer overlords take control of the steering wheel. Customers will also be able to use their Tesla fully-self driving vehicles as a type of Uber rider sharing, money making product -- a person's Tesla can generate income while they're at work or on vacation simply by tapping a Tesla app; this, according to Musk, could help dramatically lower the full cost of a Tesla. Musk's plan to produce what amounts to a self-perpetuating technology appears to run counter to his campaign against artificial intelligence.

Google acquired DeepMind in 2014 to apply machine learning and artificial intelligence in applications that could change human lives. DeepMind just announced a medical research project with an NHS Trust to combat sight loss specifically related to Diabetes and Age-related Macular Degeneration (AMD). Diabetes is on the rise. It's estimated that 1 in 11 of the world's adult population are affected. It's also the leading cause of blindness in the working age population – if you're diabetic you are 25 times more likely to suffer some kind of sight loss.

Now there is an A.I. that can do your job. Customers can direct exactly how their new website should look. This A.I. is still in a limited beta but it is coming. It's called The Grid and it came out of nowhere. It makes you feel like you are interacting with a human counterpart.

Abstract--Trajectory segmentation is the process of subdividing a trajectory into parts either by grouping points similar with respect to some measure of interest, or by minimizing a global objective function. Here we present a novel online algorithm for segmentation and summary, based on point density along the trajectory, and based on the nature of the naturally occurring structure of intermittent bouts of locomotive and local activity. We show an application to visualization of trajectory datasets, and discuss the use of the summary as an index allowing efficient queries which are otherwise impossible or computationally expensive, over very large datasets.

Nvidia this week unveiled a new, super powerful Titan X graphics card.Boasting 12 billion transistors, 3,584 CUDA cores at 1.53GHz (up from 3,072 cores at 1.08GHz in the previous Titan X), 12GB of GDDR5X memory, and more than 10 teraflops of computing performance, the 1,200 GPU began with a bet."Brian Kelleher, our top hardware engineer, bet our CEO, Jen-Hsun Huang, we could get more than 10 teraflops of computing performance from a single chip," Nvidia said in a blog post. "Jen-Hsun thought it was crazy."Well, And, as of today, Jen-Hsun now owes Brian a dollar." In a Wednesday meeting of deep-learning experts at Stanford University, Nvidia's CEO presented the Titan X to Baidu Chief Scientist Andrew Ng. Four years ago, Ng helped jumpstart the field of artificial intelligence by using GPUs to build a network of artificial neurons."If

Back on the judging panel is Professor Noel Sharkey, a robotics expert who featured on the programme for five years. Sharing memories of his time on the show, he told the BBC he was initially hesitant to take part... I was a very reluctant judge for the first series of Robot Wars. I was concerned that being on a popular TV show might damage my reputation as a university professor and as an educator. Even after the first series, I thought that I should opt out - but then something quite remarkable happened.