Pruning of redundant or irrelevant instances of data is a key to every successful solution for pattern recognition. In this paper, we present a novel ranking-selection framework for low-length but highly correlated instances. Instead of working in the low-dimensional instance space, we learn a supervised projection to high-dimensional space spanned by the number of classes in the dataset under study. Imposing higher distinctions via exposing the notion of labels to the instances, lets to deploy one versus all ranking for each individual classes and selecting quality instances via adaptive thresholding of the overall scores. To prove the efficiency of our paradigm, we employ it for the purpose of texture understanding which is a hard recognition challenge due to high similarity of texture pixels and low dimensionality of their color features. Our experiments show considerable improvements in recognition performance over other local descriptors on several publicly available datasets.

IN JULY 2011 Sebastian Thrun, who among other things is a professor at Stanford, posted a short video on YouTube, announcing that he and a colleague, Peter Norvig, were making their "Introduction to Artificial Intelligence" course available free online. By the time the course began in October, 160,000 people in 190 countries had signed up for it. At the same time Andrew Ng, also a Stanford professor, made one of his courses, on machine learning, available free online, for which 100,000 people enrolled. Both courses ran for ten weeks. Such online courses, with short video lectures, discussion boards for students and systems to grade their coursework automatically, became known as Massive Open Online Courses (MOOCs).

We're all a bit worried about the terrifying surveillance state that becomes possible when you cross omnipresent cameras with reliable facial recognition -- but a new study suggests that some of the best algorithms are far from infallible when it comes to sorting through a million or more faces. The University of Washington's MegaFace Challenge is an open competition among public facial recognition algorithms that's been running since late last year. The idea is to see how systems that outperform humans on sets of thousands of images do when the database size is increased by an order of magnitude or two. "We're the first to suggest that face recs algorithms should be tested at'planet-scale,'" wrote the study's lead author, Ira Kemelmacher-Shlizerman, in an email to TechCrunch. "I think that many will agree it's important. The big problem is to create a public dataset and benchmark (where people can compete on the same data). Creating a benchmark is typically a lot of work but a big boost to a research area."

Artificial intelligence (A.I.) and machine learning have emerged as key tools in the armory of many major tech companies, but can it be harnessed to solve some of the world's greatest challenges? IBM and Xprize want to find out. First announced back in February, the 5 million IBM Watson AI Xprize is a competition from Xprize, an initiative launched in 1995 to help solve "the world's Grand Challenges" through incentive-based prizes. Registrations for the four-year global competition are now open, with entrants asked to show how humans and A.I. can tackle issues in education, energy and the environment, health care, exploration, and global development. Xprize has given birth to numerous notable competitions in the past, one of the most recent being the Google-sponsored Lunar Xprize that's setting out to send a private, unmanned aircraft to the moon.

In a series of surveys published Thursday in the journal Science, researchers asked people what they believe a driverless car ought to do in the following scenario: A group of pedestrians are crossing the street, and the only way the car can avoid hitting them is by swerving off the road, which would kill the passengers inside. The participants generally agreed that the cars should be programmed to sacrifice their passengers if doing so would save many other people. This, broadly speaking, is a utilitarian kind of answer -- one aimed at preserving the greatest possible number of lives. But there's one problem: The people in the survey also said they wouldn't want to ride in these cars themselves. It would be OK for others to buy them, the participants said, but they personally would not.

From within the dark confines of the skull, the brain builds its own version of reality. By weaving together expectations and information gleaned from the senses, the brain creates a story about the outside world. For most of us, the brain is a skilled storyteller, but to spin a sensible yarn, it has to fill in some details itself. "The brain is a guessing machine, trying at each moment of time to guess what is out there," says computational neuroscientist Peggy Seriès. Guesses just slightly off -- like mistaking a smile for a smirk -- rarely cause harm.

Researchers asked 2,000 study participants to choose the moral course of action in accident scenarios where the number of vehicle passengers and at-risk pedestrians varied. Motor vehicle accidents caused nearly 40,000 traffic fatalities and 4.5 million serious injuries in the United States in 2015, and 90 percent of those accidents were due to human error. Remove the human component with self-driving vehicles, and many of those accidents could be preventable. Instead, computer-driven cars will face moral dilemmas where they must choose between two bad outcomes: Place a passenger in danger to save a pedestrian or vice versa. A new study argues that how these vehicles respond to ethical dilemmas could dictate their public safety and widespread adoption by consumers.

Autonomous vehicles (AVs) should reduce traffic accidents, but they will sometimes have to choose between two evils, such as running over pedestrians or sacrificing themselves and their passenger to save the pedestrians. Defining the algorithms that will help AVs make these moral decisions is a formidable challenge. We found that participants in six Amazon Mechanical Turk studies approved of utilitarian AVs (that is, AVs that sacrifice their passengers for the greater good) and would like others to buy them, but they would themselves prefer to ride in AVs that protect their passengers at all costs. The study participants disapprove of enforcing utilitarian regulations for AVs and would be less willing to buy such an AV. Accordingly, regulating for utilitarian algorithms may paradoxically increase casualties by postponing the adoption of a safer technology.

It brings a whole new meaning to the phrase'saving face'. Living bone grown from stem cells found in fat could soon be used to help reconstruct the faces of people injured in accidents or who have undergone cancer surgery. Scientists have for the first time grown large sections of bone in the laboratory before implanting them into pigs to repair damage to their jaws. The bone was grown on a scaffold inside a bioreactor (pictured) that kept it under mechanical strain to ensure it grew in a way that would be similar to bone grown in the body. The researchers say the implants can precisely replicate the original anatomical structure of the facial bone they are replacing, meaning facial features can be restored.

In catch-22 traffic emergencies where there are only two deadly options, people generally want a self-driving vehicle to, for example, avoid a group of pedestrians and instead slam itself and its passengers into a wall, a new study says. But they would rather not be travelling in a car designed to do that. The findings of the study, released on Thursday in the journal Science, highlight just how difficult it may be for auto companies to market those cars to a public that tends to contradict itself. Related: Statistically, self-driving cars are about to kill someone. "People want to live a world in which everybody owns driverless cars that minimize casualties, but they want their own car to protect them at all costs," Iyad Rahwan, a co-author of the study and a professor at MIT, said.