We introduce a new learned descriptor for audio signals which is efficient for event representation. The entries of the descriptor are produced by evaluating a set of regressors on the input signal. The regressors are class-specific and trained using the random regression forests framework. Given an input signal, each regressor estimates the onset and offset positions of the target event. The estimation confidence scores output by a regressor are then used to quantify how the target event aligns with the temporal structure of the corresponding category. Our proposed descriptor has two advantages. First, it is compact, i.e. the dimensionality of the descriptor is equal to the number of event classes. Second, we show that even simple linear classification models, trained on our descriptor, yield better accuracies on audio event classification task than not only the nonlinear baselines but also the state-of-the-art results.

The robotic skull of a T-600 cyborg used in the movie Terminator 3. Eduardo Parra/Getty Images hide caption The robotic skull of a T-600 cyborg used in the movie Terminator 3. In his lab at George Mason University in Virginia, Sean Luke has all kinds of robots: big ones with wheels, medium ones that look like humans, and then he has a couple of dozen that look like small, metal boxes. He and his team at the Autonomous Robotics Lab are training those little ones to work together without the help of a human. In the future, Luke and his team hope those little robots can work like ants -- in teams of hundreds, for example, to build houses, or help search for survivors after a disaster. "These things are changing very rapidly and they're changing much faster than we sort of expected them to be changing recently," Luke says. New algorithms and huge new databases are allowing robots to navigate complex spaces, and artificial intelligence just achieved a victory few thought would ever happen: A computer made by Google beat a professional human in a match of Go.

It's no secret that machine learning - more specifically, deep learning - has been playing an increasingly noticeable role in the world of art, as of late. From Deep Dream, to Deep Forger, to Beyond the Fence, and further, all varieties of art have been touched by the creativity of neural networks, and it seems that this has not gone unnoticed by those outside of the direct sphere of machine learning. Gene Kogan, of the Tisch School of the Arts at NYU, has recently started up his inaugural offering of Machine Learning for Artists, an elective course in the school's Interactive Telecommunications Program (ITP). The ITP has the mission of exploring "the imaginative use of communications technologies," and how they may be leveraged for bringing art and delight into the lives of individuals. They self-identify as "a Center for the Recently Possible," a term I think is fantastic.

"Can the brain do back-propagation?" Speaker Abstract and Bio can be found here: http://ee380.stanford.edu/Abstracts/1... Colloquium on Computer Systems Seminar Series (EE380) presents the current research in design, implementation, analysis, and use of computer systems. Topics range from integrated circuits to operating systems and programming languages. It is free and open to the public, with new lectures each week.

Spencer Greenberg holds a B.S. Magna Cum Laude in Applied Mathematics & Computer Science, from Columbia University, and a Ph D. in Machine Learning, from NYU. Prior to Rebellion Research, he was Software Developer, Neuberger Berman, LLC and Engineer in The Investigative Project for Terrorism. Spencer has been interviewed on CNBC, Bloomberg News, Canada's BNN, and in the Wall Street Journal. He has also lectured at Columbia School of Business, and the NYU Stern School of Business. What type of machine learning do you use for Rebellion Research's AI system? A. We apply our own proprietary machine learning approach, which performs a form of Bayesian probabilistic modeling. We have found that off the shelf machine learning solutions usually do not work very well in our problem domain.

The Yelp Restaurant Photo Classification recruitment competition ran on Kaggle from December 2015 to April 2016. Dmitrii Tsybulevskii took the cake by finishing in 1st place with his winning solution. In this blog, Dmitrii dishes the details of his approach including how he tackled the multi-label and multi-instance aspects of this problem which made this competition a unique challenge. I hold a degree in Applied Mathematics, and I'm currently working as a software engineer on computer vision, information retrieval and machine learning projects. Yes, since I work as a computer vision engineer, I have image classification experience, deep learning knowledge, and so on.

Please complete the form below to register for the webinar.

In the 2004 film I, Robot, Will Smith's character Detective Spooner harbors a deep grudge for all things technological -- and turns out to be justified after a new generation of robots engage in a full out, summer blockbuster-style revolt against their human creators. Why was Detective Spooner such a Luddite–even before the Robots' vicious revolt? Much of his resentment stems from a car accident he endured in which a robot saved his life instead of a little girl's. The robot's decision haunts Smith's character throughout the movie; he feels the decision lacked emotion, and what one might call'humanity'. "I was the logical choice," he says. "(The robot) calculated that I had a 45% chance of survival. Sarah only had an 11% chance." He continues, dramatically, "But that was somebody's baby. A human being would've known that."

For years, Person of Interest has been right on the cutting edge between commenting on current events and speculating about the future. With its final season, the show is depicting a futuristic nightmare--and yet, it's also more topical than ever before. We talked to producers Jonathan Nolan and Greg Plageman, and they told us the real villain of Person of Interest is Facebook. First off, I've seen the season premiere of Person of Interest, which airs next Tuesday, May 3. True to form, it's a brilliant hour of television that will keep you throwing things at your TV screen as the Machine Gang struggles to come back from their devastating loss at the end of season four. The super-intelligent Machine, which was built to predict terrorist threats but wound up trying to save ordinary people from smaller crimes, has been destroyed, and the race to reconstruct it from some memory chips is as intense as any thriller I've seen in ages. I honestly don't know what I can say about Person of Interest that we haven't said a dozen times before--this is one of the best science fiction shows of the past decade.

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