Using computers to view the unseen
A new computational imaging method could change how we view hidden information in scenes.
Rachel Gordon | CSAIL | Dec. 6, 2019 | mit~7 mins
Tags: computer-science-and-artificial-intelligence-laboratory-csail electrical-engineering-and-computer-science-eecs school-of-engineering research algorithms computer-science-and-technology computer-vision video-games video disaster-response film-and-television
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.
Rob Matheson | MIT News Office | Dec. 2, 2019 | mit~9 mins
Tags: research computer-science-and-technology algorithms artificial-intelligence machine-learning computer-vision computer-science-and-artificial-intelligence-laboratory-csail brain-and-cognitive-sciences electrical-engineering-computer-science-eecs school-of-engineering center-for-brains-minds-and-machines
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?
Adam Conner-Simons | Rachel Gordon | MIT CSAIL | Nov. 18, 2019 | mit~7 mins
Tags: electrical-engineering-and-computer-science-eecs school-of-engineering robotics robots artificial-intelligence automobiles autonomous-vehicles research computer-vision transportation machine-learning behavior computer-science-and-artificial-intelligence-laboratory-csail
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.
Rob Matheson | MIT News Office | Oct. 25, 2019 | mit~7 mins
Tags: research aeronautical-and-astronautical-engineering school-of-engineering computer-science-and-technology algorithms autonomous-vehicles drones robots robotics computer-vision technology-and-society
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.
Rachel Gordon | MIT CSAIL | June 17, 2019 | mit~6 mins
Tags: computer-science-and-artificial-intelligence-laboratory-csail school-of-engineering electrical-engineering-computer-science-eecs machine-learning computer-vision networks data research algorithms artificial-intelligence computer-science-and-technology brain-and-cognitive-sciences robotics
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.
Sabbi Lall | McGovern Institute for Brain Research | April 29, 2019 | mit~6 mins
Tags: school-of-science brain-and-cognitive-sciences mcgovern-institute center-for-brains-minds-and-machines artificial-intelligence computer-vision autonomous-vehicles national-science-foundation-nsf research
Deep-learning technique reveals “invisible” objects in the dark
Method could illuminate features of biological tissues in low-exposure images.
Jennifer Chu | MIT News Office | Dec. 12, 2018 | mit~9 mins
Tags: algorithms artificial-intelligence machine-learning computer-vision mechanical-engineering research school-of-engineering
Fleets of drones could aid searches for lost hikers
System allows drones to cooperatively explore terrain under thick forest canopies where GPS signals are unreliable.
Rob Matheson | MIT News Office | Nov. 1, 2018 | mit~7 mins
Tags: research algorithms computer-science-and-technology autonomous-vehicles drones aeronautical-and-astronautical-engineering robotics robots computer-vision technology-and-society nasa computer-science-and-artificial-intelligence-laboratory-csail electrical-engineering-computer-science-eecs school-of-engineering
Machines that learn language more like kids do
Computer model could improve human-machine interaction, provide insight into how children learn language.
Rob Matheson | MIT News Office | Oct. 31, 2018 | mit~9 mins
Tags: research language machine-learning artificial-intelligence data computer-vision human-computer-interaction mcgovern-institute center-for-brains-minds-and-machines robots robotics national-science-foundation-nsf computer-science-and-technology computer-science-and-artificial-intelligence-laboratory-csail electrical-engineering-computer-science-eecs school-of-engineering
Recognizing the partially seen | MIT News
Advances in computer vision inspired by human physiological and anatomical constraints are improving pattern completion in machines.
Kris Brewer | Center for Brains, Minds and Machines | Sept. 20, 2018~4 mins |
Tags: artificial-intelligence machine-learning computer-vision school-of-science brain-and-cognitive-sciences research computer-modeling center-for-brains-minds-and-machines mcgovern-institute
Page 1 of 5