Generative Adversarial Networks have shown remarkable success in learning a distribution that faithfully recovers a reference distribution in its entirety. However, in some cases, we may want to only learn some aspects (e.g., cluster or manifold structure), while modifying others (e.g., style, orientation or dimension). In this work, we propose an approach to learn generative models across such incomparable spaces, and demonstrate how to steer the learned distribution towards target properties. A key component of our model is the Gromov-Wasserstein distance, a notion of discrepancy that compares distributions relationally rather than absolutely. While this framework subsumes current generative models in identically reproducing distributions, its inherent flexibility allows application to tasks in manifold learning, relational learning and cross-domain learning.

Virgin's internet service appears to have stopped working, with people unable to get online. The company's mobile data service appears to have broken for at least some users, who are unable to make calls or get online. The issues started around lunchtime, according to the website Down Detector. They were reported across the country, it said. While the Virgin Media Twitter account has been hit by a huge number of complaints, it has yet to respond to the problems publicly.

Artificial Intelligence (AI) software that forms an opinion of people by the way they speak - in much the same way people do - is being developed by a UK finance firm. The language and vocabulary used by customers who ring in seeking help with their mortgage or savings accounts will be used to create a profile. The system, which is being backed by the Nationwide Building Society, will then tailor a computer generated conversation with the customer defined by their'voice personality'. Artificial Intelligence (AI) software that forms an opinion of people by the way they speak - in much the same way people do - is being developed by a UK finance firm. The AI system, developed by the company Scaled Insights, is already being used in partnership with hospitals in Leeds to help communicate with patients in the treatment of obesity and other issues.

An Elon Musk-backed startup looking to connect human brains to computers has raised most of its $51 million funding target. According to a report by Bloomberg, Neuralink has raised $39 million of its planned $51 million funding round as per a filing with the Securities and Exchange Commission (SEC). Prior funding rounds date back two years when the company raised $27 million after aiming for as much as $100 million. While it's unclear what progress Neuralink has made in its technology, if any, the filings come less than a month after the SpaceX and Tesla CEO foreshadowed the startup's endeavors in an ambiguous tweet. In a response on Twitter, Musk said Neuralink technology is'coming soon.' Elon Musk believes humans must link up with machines in order to fight the inevitable onslaught of artificial intelligence.

Though it may sound like something from science fiction, brain zapping -- or neuro-electrostimulation, as it's known -- is already being used to treat a variety of ailments. Researchers at Boston University recently reported that zapping the brains of older people could restore their thinking powers to those of someone in their 20s. 'Neuro-electrostimulation makes sense because the brain is an organ that works by electrical impulses, and there are many different techniques that can alter the brain's electrical activity, possibly for a therapeutic effect,' says Dr Lucia Li, a neurologist and clinical lecturer at Imperial College London. The brain-zapping treatment can be given via caps, headbands, or electrodes stuck to the scalp or even implanted in the brain. In some types of treatment, such as electroconvulsive therapy, used to treat severe depression, brain zapping is so powerful, patients have to be anaesthetised in case they hurt themselves.

South Korea is developing robots that mimic wildlife adapted for all environments on Earth for military warfare. The nature inspired technology, known as biomimetics, will form part of the country's future weapons systems and help its soldiers in battles. Robot designs inspired by birds, snakes and marine species aim to cover both surveillance and combat via sea, land and sky. It is an attempt to catch up with neighbouring countries such as China and Russia who have made huge advances in the application of the technology, said a defence agency personnel. South Korea is developing a range of robots that mimic wildlife adapted for all environments on Earth for military warfare.

Alexa's got a new gig: home safety. Amazon today introduces Alexa Guard, a free feature that uses the microphones of the Amazon Echo speakers to listen for the sounds of smoke and carbon monoxide alarms or breaking glass. Should the personal assistant hear any of those, it will send text alerts to your phone. Amazon says it's introducing the feature to "help you keep your home safe." Amazon says that security devices, such as the Ring video doorbell, which Amazon owns, or ADT Pulse, which it doesn't, can work with Guard in that Alexa will send the alerts to the security provider. Additionally, Alexa can be programmed to have smart, connected lights turn on and off remotely when you're out "to make it look like you're home while you're away," says Amazon.

Liz O'Sullivan says she struggled for months as she learned more about the military project her in which her employer, Clarifai, was participating. Liz O'Sullivan says she struggled for months as she learned more about the military project her in which her employer, Clarifai, was participating. On the night of Jan. 16, Liz O'Sullivan sent a letter she'd been working on for weeks. It was directed at her boss, Matt Zeiler, the founder and CEO of Clarifai, a tech company. "The moment before I hit send and then afterwards, my heart, I could just feel it racing," she says.

A technician works in a lab at GeseDNA Technology in Beijing. To counter China, the U.S. plans to impose new export restrictions on "emerging and foundational technology" that researchers say could affect the way they share genetic materials with international labs. A technician works in a lab at GeseDNA Technology in Beijing. To counter China, the U.S. plans to impose new export restrictions on "emerging and foundational technology" that researchers say could affect the way they share genetic materials with international labs. For the last 15 years, Addgene has dedicated itself to accelerating medical research.

Welcome to the fourth installment in our Call For Code Technology mini-series where I identify and explore one of the six core technology focus areas within Call For Code. You'll learn about a technology, how to best use it on IBM Cloud, and where to find the best resources to fuel your innovation. If you missed any of my other blog posts on building applications for Call for Code, check out my posts on IoT and Node-RED, AI and blockchain. First things first: If you haven't already done so, accept the Call for Code challenge and join our community. Here in Part 4, I talk about integrating machine learning into your Call for Code solution.