MIT Libraries explore 17th-century postal archive in "Signed, Sealed, and Undelivered"
2,600 recently rediscovered early modern letters to be analyzed in groundbreaking international digital humanities project.
Computer Science and Artificial Intelligence Laboratory (CSAIL)
Amplifying — or removing — visual variation
Algorithms could offer new tools for graphics software or reveal structural defects.
How to make better visualizations
Eye-tracking research reveals which types of visuals actually get the message across.
System automatically converts 2-D video to 3-D
Exploiting video game software yields broadcast-quality 3-D video of soccer games in real time.
Real-time epidemiology from urban wastewater
MIT and Kuwait researchers have been awarded $4 million to fund Underworlds, a study of real-time epidemiology using biomarkers in urban sewage.
How wireless “X-ray vision” could power virtual reality, smart homes, and Hollywood
By seeing silhouettes through a wall, CSAIL device could help with motion capture, fall prevention and even your heating bill.
A basis for all cryptography
A tool that would provide a secure foundation for any cryptographic system may be close at hand.
Faster optimization
New general-purpose optimization algorithm promises order-of-magnitude speedups on some problems.
Automating big-data analysis
System that replaces human intuition with algorithms outperforms 615 of 906 human teams.
Predicting change in the Alzheimer’s brain
Combining MRI and other data helps machine-learning systems predict effects of neurodegenerative disease.
More-flexible machine learning
Giving machine-learning systems “partial credit” during training improves image classification.
Soft robotic hand can pick up and identify a wide array of objects
Team from Computer Science and Artificial Intelligence Lab develops silicone rubber gripper and advanced object-identification algorithms.
Learning language by playing games
System learns to play text-based computer game using only linguistic information.
Personalized heart models for surgical planning
System can convert MRI scans into 3D-printed, physical models in a few hours.
Learning spoken language
System learns to distinguish words’ phonetic components, without human annotation of training data.