The availability of graph data with node attributes that can be either discrete or real-valued is constantly increasing. While existing kernel methods are effective techniques for dealing with graphs having discrete node labels, their adaptation to non-discrete or continuous node attributes has been limited, mainly for computational issues. Recently, a few kernels especially tailored for this domain, and that trade predictive performance for computational efficiency, have been proposed. In this paper, we propose a graph kernel for complex and continuous nodes' attributes, whose features are tree structures extracted from specific graph visits. The kernel manages to keep the same complexity of state-of-the-art kernels while implicitly using a larger feature space. We further present an approximated variant of the kernel which reduces its complexity significantly. Experimental results obtained on six real-world datasets show that the kernel is the best performing one on most of them. Moreover, in most cases the approximated version reaches comparable performances to current state-of-the-art kernels in terms of classification accuracy while greatly shortening the running times.

Over the last years, huge resources of biological and medical data have become available for research. This data offers great chances for machine learning applications in health care, e.g. for precision medicine, but is also challenging to analyze. Typical challenges include a large number of possibly correlated features and heterogeneity in the data. One flourishing field of biological research in which this is relevant is epigenetics. Here, especially large amounts of DNA methylation data have emerged. This epigenetic mark has been used to predict a donor's 'epigenetic age' and increased epigenetic aging has been linked to lifestyle and disease history. In this paper we propose an adaptive model which performs feature selection for each test sample individually based on the distribution of the input data. The method can be seen as partially blind domain adaptation. We apply the model to the problem of age prediction based on DNA methylation data from a variety of tissues, and compare it to a standard model, which does not take heterogeneity into account. The standard approach has particularly bad performance on one tissue type on which we show substantial improvement with our new adaptive approach even though no samples of that tissue were part of the training data.

IN the summer of 1956, a remarkable collection of scientists and engineers gathered at Dartmouth College in Hanover, New Hampshire. Among them were computer scientist Marvin Minsky, information theorist Claude Shannon and two future Nobel prizewinners, Herbert Simon and John Nash. Their task: to spend the summer months inventing a new field of science called "artificial intelligence" (AI). They did not lack in ambition, writing in their funding application: "every aspect of learning or any other feature of intelligence can in principle be so precisely described that a machine can be made to simulate it." Their wish list was "to make machines use language, form abstractions and concepts, solve kinds of problems now reserved for humans, and improve themselves". They thought that "a significant advance can be made in one or more of these problems if a carefully selected group of scientists work on it together for a summer."

Researchers and engineers from BMW are working at IBM's Munich headquarters for its Watson Internet of Things (IoT) technology. They'll help develop IBM's Watson cognitive system, which can learn from and pass back intelligence into the physical world, for integration into automotive products. BMW is providing the IBM site with four i8s to be used as prototypes for these new artificial intelligence systems. The systems will run on IBM's Bluemix cloud platform, which IBM said will enable Watson technology to heighten a driver's connection with their car. The technology uses machine learning to enable a car to improve its understanding of its driver, so it can cater its systems and cabin experience to suit their preferences.

This is the first installment in a three-part review of 2016 in machine learning and deep learning. In Part Two, we cover developments in each of the leading open source machine learning and deep learning projects. Part Three will review the machine learning and deep learning moves of commercial software vendors. As organizations expand the use of machine learning for profiling and automated decisions, there is growing concern about the potential for bias. In 2016, reports in the media documented racial bias in predictive models used for criminal sentencing, discriminatory pricing in automated auto insurance quotes, an image classifier that learned "whiteness" as an attribute of beauty, and hidden stereotypes in Google's word2vec algorithm.

The TechCrunch conference is an event that swoops in on the startup scenes of the US and Europe, gathering for appraisal the technology world's rising movers, shakers and innovators. It's widely regarded as the place to get a feel for what's happening at the industry's grassroots – which is exactly what PwC Innovation Manager Marina Paronetto headed to London to do. As it turns out, it was the brains behind the machine – artificial intelligence – that was the star of 2016's show. It was said in sarcasm, but MC Jordan Crook couldn't have been more accurate when she said that TechCrunch's theme for its latest Disrupt conference was artificial intelligence. From what I saw, every solution on show here featured an element of AI.

Stunning Cassini image appears to show Saturn's moon Mimas crashing into its giant rings (but NASA says its just an optical illusion) Mimas is actually 28,000 miles (45,000 kilometers) away from the rings The gravitational pull of Mimas creates waves in Saturn's rings that are visible in some Cassini images The gravitational pull of Mimas creates waves in Saturn's rings that are visible in some Cassini images Saturn's moon Mimas appears to be crashing through its rings - but it's just an optical illusion. NASA's Cassini spacecraft Mimas is actually 28,000 miles (45,000 kilometers) away from the rings. Santa ISN'T sexist if he gives your daughter a doll:... From reacting to a bad gift to buying the perfect present:... Why you shouldn't feed garden birds in spring: Putting out... The biggest map of our universe yet: Chart shows billions of... BlackBerry sets its sights on self driving cars: Firm... What is REALLY going on in North Korea? Santa ISN'T sexist if he gives your daughter a doll:... From reacting to a bad gift to buying the perfect present:... Why you shouldn't feed garden birds in spring: Putting out...

How safe is your fitness tracker? Devices like the Fitbit, Samsung Gear, Microsoft Band and Jawbone are becoming increasingly popular among fitness fanatics. But a new report has warned companies could be feeding users' personal information to private healthcare and insurance companies The new report was released by researchers at American University and the Center for Digital Democracy in Washington. BlackBerry sets its sights on self driving cars: Firm... From reacting to a bad gift to buying the perfect present:... Move over Skype: Facebook trials group audio calls for... Terrifying 13ft Avatar robot takes its first steps:... BlackBerry sets its sights on self driving cars: Firm... From reacting to a bad gift to buying the perfect present:... Move over Skype: Facebook trials group audio calls for... Terrifying 13ft Avatar robot takes its first steps:... Identify theft, data leaks, discrimination from employers and increasing insurance costs are just some of the fallout predicted from the rise of wearable technology. At over seven feet tall, is Freddy Britain's biggest dog?

Building the AI'butler' is Zuckerberg's personal challenge for 2016 The 31-year-old said: 'You can think of it kind of like J.A.R.V.I.S in Iron Man' His plans include teaching the assistant to let friends into his home by looking at their faces when they ring the doorbell, for example Building the AI'butler' is Zuckerberg's personal challenge for 2016 The 31-year-old said: 'You can think of it kind of like J.A.R.V.I.S in Iron Man' The AI is able to do everything from recognise friend's faces at the door to work out who is asking it questions - and Zuckerberg said he's even connected up a 1950s toaster and a t-shirt cannon to it. Watch as Nasa shake tests the Orion capsule that could take... Airlines add'fire containment bags' for overheating phones... Google and Facebook to install giant 8,000-mile internet... EXCLUSIVE: Royal Navy trials robot spy boats that can scour... Watch as Nasa shake tests the Orion capsule that could take... Airlines add'fire containment bags' for overheating phones... Google and Facebook to install giant 8,000-mile internet... EXCLUSIVE: Royal Navy trials robot spy boats that can scour... Zuckerberg also programmed the system to play music. Zuckerberg's daughter, Max is also able to use the AI to play. The project is modelled on the J.A.R.V.I.S. stands for (Just A Rather Very Intelligent System) system used by Tony Stark in the Iron Man films. 'I'll do in a heartbeat if Bettany gets paid and donates it to a cause of Cumberbatch's choosing...that's the right kind of STRANGE!' the Iron Man actor responded.

Sex bots could KILL: Experts warn owners'risk over-exertion' as 40% of men admit they would use one Study found that 40% of men said they'd buy a sex robot now or within 5 years The researchers surveyed 263 heterosexual men between ages 18 and 67 But, experts have warned they could cause humans to over-exert themselves Study found that 40% of men said they'd buy a sex robot now or within 5 years Nearly half of men could see themselves buying a sex robot in the near future. But, if they aren't careful, the tireless robots could push their human lovers over the edge, experts have warned. Is the treatment for woodworm the secret of why the £36... How many dots do YOU see? Try the'blind spot' optical... How safe is your fitness tracker? Hackers could steal your... Elon Musk's plan to tackle traffic: Billionaire says he'll... Is the treatment for woodworm the secret of why the £36... How many dots do YOU see?