Presenting their work at this year's Conference on Neural Information Processing Systems, Prof. Josh Tenenbaum and one of his students, Jiajun Wu, are co-authors on four papers that examine the fundamental cognitive abilities that an intelligent agent requires to navigate the world: discerning distinct objects and inferring how they respond to physical forces.
An international team of researchers, affiliated with South Korea's Ulsan National Institute of Science and Technology (UNIST) has presented a core technology for quantum photonic devices used in quantum information processing. Their work has been published in the November issue of the prestigious journal, Nano Letters.
Video games may have a reputation for attracting introverts, but when it comes to augmented reality games like Pokémon Go, extroverts tend to be better players. That's the key finding of a new University of British Columbia psychology study, the first to look at the impact of players' personalities, social competence and social anxiety when playing the hit mobile game.
As state voter identification (ID) laws across the country are being contested amid questions about the integrity of the voting process, researchers have developed a new statistical method that not only matches multiple records with precision, but can also identify the scope of discrimination when applied to voter ID laws.
In several recent papers, researchers from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) and the Qatar Computing Research Institute have used a recently developed interpretive technique, which had been applied in other areas, to analyze neural networks trained to do machine translation and speech recognition.
The new generation of 5G mobile networks is the future of the Information and Communication Technologies (ICT) sector -- a true technological revolution that will deliver the Internet of Things and is being driven by R&D+i initiatives like '5TONIC,' Spain's leading 5G innovation laboratory.
Improved recommendation algorithm should work especially well when ratings data are 'sparse.'
A group led by a University of Maryland computer scientist has designed a new algorithm that incorporates artificial neural networks to simultaneously apply a wide range of fixes to corrupted digital images. The researchers tested their algorithm by taking high-quality, uncorrupted images, purposely introducing severe degradations, then using the algorithm to repair the damage. In many cases, the algorithm outperformed competitors' techniques, very nearly returning the images to their original state.
UW engineers have developed the first 3-D printed plastic objects that can connect to other devices via WiFi without using any electronics, including a laundry bottle that can detect when soap is running low and automatically order more.
Researchers from Aalto University and University of Rome Tor Vergata have designed an algorithm that is able to balance the information exposure so that social media users can be exposed to information from both sides of the discussion.