Writing for the Financial Times, Clive Cookson reports that MIT researchers have developed an artificial intelligence system capable of producing realistic sounds for silent movies. Cookson explains that another application for the system could be “to help robots understand objects’ physical properties and interact better with their surroundings."
Washington Post reporter Matt McFarland writes that MIT researchers have created an algorithm that can produce realistic sounds. “The findings are an example of the power of deep learning,” explains McFarland. “With deep learning, a computer system learns to recognize patterns in huge piles of data and applies what it learns in useful ways.”
Popular Science reporter Mary Beth Griggs writes that MIT researchers have developed an algorithm that can learn how to predict sound. The algorithm “can watch a silent movie and create sounds that go along with the motions on screen. It's so good, it even fooled people into thinking they were actual, recorded sounds from the environment.”
Cade Metz writes for Wired that MIT researchers have developed a system that allows robots to predict how objects will move. Postdoc Ilker Yildirim explains that in order for a robot to be able to assist with household tasks like washing the dishes, it must “deeply understand its physical environments.”
MIT computer scientists have developed a program that can predict how objects will move with the same accuracy as humans, reports Mary Beth Griggs for Popular Science. The researchers hope to eventually be able to program the system to “make predictions in the natural world even faster than we can.”
An AI system created by MIT researchers can predict how physical objects move through the world with human-like accuracy, reports Curt Woodward for BetaBoston. “Where humans learn to make such judgments intuitively, we essentially had to teach the system each of these properties,” explains postdoc Ilker Yildirim.
MIT researchers have created an algorithm that can identify what traits make an image memorable, reports Matt McFarland for The Washington Post. The algorithm could prove useful in developing educational tools as “textbooks and teaching aids could start to use visual aids that have been proven to stick in our heads,” McFarland explains.
In an article for The Washington Post about artificial intelligence, Joel Achenbach speaks with MIT researchers about the future of the field. Speaking about the current state of AI, Prof. Daniela Rus explains that “there are tasks that are very easy for humans — clearing your dinner table, loading the dishwasher, cleaning up your house — that are surprisingly difficult for machines.”
MIT researchers have developed an algorithm that can predict the memorability of images with human-like accuracy, reports Adrienne Lafrance for The Atlantic. The researchers explained that their work demonstrates that “predicting human cognitive abilities is within reach for the field of computer vision.”
Boston.com reporter Megan McGinnes writes that MIT researchers are developing software that can predict how well people will remember certain images. Users of the new software “can feed images into the database, which are then overlaid with a heat map to show regions of the photo viewers are most likely to remember.”
CSAIL researchers have developed an algorithm that can predict the memorability of an image with near-human accuracy, reports Curt Woodward for BetaBoston. Woodward explains that “the technology could be used to make learning materials more memorable and advertising pitches more effective.”
A new learning program developed by researchers from MIT, NYU and the University of Toronto imitates the way humans learn, according to EFE. The researchers aim to “reduce the difference in learning capability between humans and machines.”
Researchers from MIT, NYU and the University of Toronto have created a learning program that can grasp new concepts just like humans do, reports Will Dunham for Reuters. “Judges found the work produced by the computers to be virtually indistinguishable from that of human subjects,” explains Dunham.
A new advance in machine learning allows a computer program to recognize and draw handwritten characters based off a few examples, reports John Markoff for The New York Times. Markoff explains that the “improvements are noteworthy because so-called machine-vision systems are becoming commonplace in many aspects of life.”
Joel Achenbach reports for The Washington Post on the new program developed by researchers from MIT, NYU and the University of Toronto that can learn by example, a characteristic of human learning. Prof. Joshua Tenenbaum explains that the new system has made “a significant advance in capturing the way that people are thinking about these concepts.”