Unsupervised learning on imbalanced data is challenging because, when given imbalanced data, current model is often dominated by the major category and ignores the categories with small amount of data. We develop a latent variable model that can cope with imbalanced data by dividing the latent space into a shared space and a private space. Based on Gaussian Process Latent Variable Models, we propose a new kernel formulation that enables the separation of latent space and derives an efficient variational inference method. The performance of our model is demonstrated with an imbalanced medical image dataset.

Enforcing local consistencies in cost function networks is performed by applying so-called Equivalent Preserving Transformations (EPTs) to the cost functions. As EPTs transform the cost functions, they may break the property that was making local consistency enforcement tractable on a global cost function. A global cost function is called tractable projection-safe when applying an EPT to it is tractable and does not break the tractability property. In this paper, we prove that depending on the size r of the smallest scopes used for performing EPTs, the tractability of global cost functions can be preserved (r = 0) or destroyed (r > 1). When r = 1, the answer is indefinite. We show that on a large family of cost functions, EPTs can be computed via dynamic programming-based algorithms, leading to tractable projection-safety. We also show that when a global cost function can be decomposed into a Berge acyclic network of bounded arity cost functions, soft local consistencies such as soft Directed or Virtual Arc Consistency can directly emulate dynamic programming. These different approaches to decomposable cost functions are then embedded in a solver for extensive experiments that confirm the feasibility and efficiency of our proposal.

Even top guns do not have the ability to predict poor weather or foresee obstacles in their flight path. But a new helmet-mounted display could be a pilot's'eye in the sky', as it has the ability to see through even the thickest fog and create digital images of on coming obstacles The technology combines terrain information and sensor readings to show speed, altitude and position - all displayed alongside digitally outlines of the landscape in front of the pilot's line of sight. Using augmented reality, researcher developed a system that combines terrain information and sensor readings to display speed, altitude and position alongside digital images of any obstacles. All of the data from outside is processed aboard the aircraft and projected directly to the see-through head-mounted display. This gives the pilot an ability to see obstacles with his own eyes and also view digitally generated outlines of the landscape and other potential obstacles.

The traditional definition of artificial intelligence is the ability of machines to execute tasks and solve problems in ways normally attributed to humans. Some tasks that we consider simple--recognizing an object in a photo, driving a car--are incredibly complex for AI. Machines can surpass us when it comes to things like playing chess, but those machines are limited by the manual nature of their programming; a 30 gadget can beat us at a board game, but it can't do--or learn to do--anything else. This is where machine learning comes in. Show millions of cat photos to a machine, and it will hone its algorithms to improve at recognizing pictures of cats.

Wang Jun spent 16 years expanding the world's understanding of what living things are made of -- sequencing genomes including those of the giant panda and potatoes. Now he's attempting to build on that: using DNA as one component to create online avatars that could act as health-care test dummies for people. Asia's biggest internet company believes he's onto something. Wang's iCarbonX wants to construct a "digital you" containing biological samples such as saliva, proteins and DNA; bolstered by environmental measurements such as air quality; and lifestyle factors such as workout regimes and diet. The Shenzhen, China-based company is developing algorithms to analyze the data, with the intention of recommending tailored wellness programs, food choices and possibly prescription medicines.

As yet another deadly attack on Tuesday tore through Turkey's biggest airport, Mark Cuban is demanding action. The billionaire businessman, appearing on Megyn Kelly's Fox Business show the same night, called for both presumptive presidential candidates to do more than just say'this is bad.' Cuban proposed that the country look to technological innovations for a solution. "How do you deal with immigration? How do you deal with radical Islamic terrorists trying to come into the country? You're going to need to use tech," said Cuban, in a Bloomberg interview earlier this week. Both the Republican and Democrat would-be nominees are technologically illiterate, he said to Bloomberg's Cory Johnson, which is the reason they are blind to technological solutions to the country's biggest issues.

In June of 1975, the Office of the White House Press Secretary announced President Gerald R. Ford's picks for the National Medal of Science. One went to the Austrian-born mathematician and logician Kurt Gödel. Nicknamed Mr. Why by his parents, Gödel was known to a subset of his constituents as, simply, God. He received fan mail from all over the world, archiving it into files of "autograph requests," "inquiries from students and amateurs," "letters of appreciation," and "crank correspondence." A self-described "dunce fool of Mathematics" in West Bengal wrote seeking Gödel's "Guruship," and a svelte math teacher in California confessed that she'd taken the liberty of enlarging a photo of Gödel to make a poster for her classroom.

During the recent Consumer Goods Forum global summit here in Cape Town, I had the opportunity to briefly chat with Vivienne about some of the issues confronting the digital disruption of this industry sector. [The original transcript has been edited for clarity and space.] Named one of 10 Women to Watch in Tech in 2013 by Inc. Magazine, Vivienne Ming is a theoretical neuroscientist, technologist and entrepreneur. She co-founded Socos, where machine learning and cognitive neuroscience combine to maximize students' life outcomes. Vivienne is a visiting scholar at UC Berkeley's Redwood Center for Theoretical Neuroscience, where she pursues her research in neuroprosthetics. In her free time, Vivienne has developed a predictive model of diabetes to better manage the glucose levels of her diabetic son and systems to predict manic episodes in bipolar suffers. She sits on the boards of StartOut, The Palm Center, Emozia, and the Bay Area Rainbow Daycamp, and is an advisor to Credit Suisse, Cornerstone Capital, and BayesImpact. Dr. Ming also speaks frequently on issues of LGBT inclusion and gender in technology. Every once in a while I have the opportunity to discuss wide-ranging topics with an intellect that stimulates, is passionate and really cares about the bigger picture. Those opportunities are more rare than one would think. Although set in a somewhat unexpected venue (the elite innards of consumer capitalism) her observations on the inescapable disruption that the new wave of modern technologies are prescient and thoughtful. Ed: In a continent where there is a large focus on putting people to work, how do you see the challenges and disruptions resulting from AI, robotics, IoT, VR and other technologies playing out? These technologies, as did other disruptive technologies before them, tend to replace human workers with machine processes. Vivienne: There is almost no domain in which artificial intelligence (AI), machine learning and automation will not have a profound and positive impact. Medicine, farming, transportation, etc. will all benefit. There will be a huge impact on human potential, and human work will change. I think this is inevitable, that we are well on the way to this AI-enabled future.

Frances O'Connor expected questions about what it was like to work with Steven Spielberg. And perhaps queries about exactly how Spielberg managed to take over his good friend Stanley Kubrick's dream project, A.I. Artificial Intelligence – writing and shooting in less than two years a dark, futuristic fairy tale that Kubrick had not been able to pull together in two decades. What the 31-year-old Australian actress didn't expect were tirades from reporters about the way her A.I. character, Monica Swinton, discards her robotic surrogate son, David (Haley Joel Osment). Monica can't handle David's intense form of programmed love – and she'd rather abandon him to wander a cruel future world than see him destroyed by his manufacturer, the fate of all returned robot merchandise in A.I.'s harsh universe. The resulting Sophie's Choice/Medea dilemma all but short-circuited one female TV journalist, who appeared before O'Connor trembling with indignation.

Justine Cassell has taken her virtual assistant Sara on a road trip. They're in Tianjin, China, where Carnegie Mellon University's associate dean of technology strategy and impact traveled to offer a glimpse of tomorrow at this week's Annual Meeting of New Champions. Sara, for "socially aware robot assistant," has spent the past several days greeting hundreds of people coming to the event, hosted by the World Economic Forum, at a station showcasing the office of the future. A life-size face and torso on a big-screen TV, Sara served as the front end to the event app. That presentation might make you think of Max Headroom, the stuttering AI character from the 1980s show.