Identifying a melody by studying a musician’s body language
Music gesture artificial intelligence tool developed at the MIT-IBM Watson AI Lab uses body movements to isolate the sounds of individual instruments.
Tags: machine-learning artificial-intelligence music research school-of-engineering school-of-science computer-science-and-technology algorithms brain-and-cognitive-sciences computer-science-and-artificial-intelligence-laboratory-csail quest-for-intelligence computer-vision electrical-engineering-and-computer-science-eecs mit-schwarzman-college-of-computing
A new model of vision
Computer model of face processing could reveal how the brain produces richly detailed visual representations so quickly.
Tags: machine-learning neuroscience artificial-intelligence research school-of-engineering school-of-science brain-and-cognitive-sciences computer-science-and-artificial-intelligence-laboratory-csail center-for-brains-minds-and-machines national-science-foundation-nsf computer-vision
To self-drive in the snow, look under the road
Weather’s a problem for autonomous cars. MIT’s new system shows promise by using “ground-penetrating radar” instead of cameras or lasers.
Tags: robotics machine-learning artificial-intelligence research autonomous-vehicles transportation automobiles school-of-engineering faculty computer-science-and-artificial-intelligence-laboratory-csail computer-vision lincoln-laboratory electrical-engineering-and-computer-science-eecs mit-schwarzman-college-of-computing distributed-robotics-laboratory
Bridging the gap between human and machine vision
Researchers develop a more robust machine-vision architecture by studying how human vision responds to changing viewpoints of objects.
Tags: machine-learning artificial-intelligence research school-of-science computer-science-and-technology brain-and-cognitive-sciences center-for-brains-minds-and-machines computer-vision
Using computers to view the unseen
A new computational imaging method could change how we view hidden information in scenes.
Tags: video research video-games school-of-engineering computer-science-and-technology algorithms computer-science-and-artificial-intelligence-laboratory-csail computer-vision disaster-response film-and-television electrical-engineering-and-computer-science-eecs
Helping machines perceive some laws of physics
Model registers “surprise” when objects in a scene do something unexpected, which could be used to build smarter AI.
Tags: machine-learning artificial-intelligence research school-of-engineering electrical-engineering-computer-science-eecs computer-science-and-technology algorithms brain-and-cognitive-sciences computer-science-and-artificial-intelligence-laboratory-csail center-for-brains-minds-and-machines computer-vision
Predicting people's driving personalities
System from MIT CSAIL sizes up drivers as selfish or selfless. Could this help self-driving cars navigate in traffic?
Tags: robotics machine-learning artificial-intelligence robots research autonomous-vehicles transportation automobiles behavior school-of-engineering computer-science-and-artificial-intelligence-laboratory-csail computer-vision electrical-engineering-and-computer-science-eecs
System prevents speedy drones from crashing in unfamiliar areas
Drones can fly at high speeds to a destination while keeping safe “backup” plans if things go awry.
Tags: robotics robots research autonomous-vehicles drones school-of-engineering computer-science-and-technology technology-and-society algorithms aeronautical-and-astronautical-engineering computer-vision
Teaching artificial intelligence to connect senses like vision and touch
MIT CSAIL system can learn to see by touching and feel by seeing, suggesting future where robots can more easily grasp and recognize objects.
Tags: robotics machine-learning artificial-intelligence data networks research school-of-engineering electrical-engineering-computer-science-eecs computer-science-and-technology algorithms brain-and-cognitive-sciences computer-science-and-artificial-intelligence-laboratory-csail computer-vision
For better deep neural network vision, just add feedback (loops)
The DiCarlo lab finds that a recurrent architecture helps both artificial intelligence and our brains to better identify objects.
Tags: artificial-intelligence research autonomous-vehicles school-of-science brain-and-cognitive-sciences center-for-brains-minds-and-machines national-science-foundation-nsf mcgovern-institute computer-vision
Page 1 of 6