Cryptographic protocol enables greater collaboration in drug discovery
Neural network that securely finds potential drugs could encourage large-scale pooling of sensitive data.
Computer Science and Artificial Intelligence Laboratory (CSAIL)
A step toward personalized, automated smart homes
System that automatically identifies people moving around indoors could enable self-adjusting homes.
Automated system identifies dense tissue, a risk factor for breast cancer, in mammograms
Deep-learning model has been used successfully on patients, may lead to more consistent screening procedures.
Model helps robots navigate more like humans do
In simulations, robots move through new environments by exploring, observing, and drawing from learned experiences.
Detecting fake news at its source
Machine learning system aims to determine if an information outlet is accurate or biased.
3Q: Antonio Torralba on what's next for the Quest for Intelligence
Inaugural director of The Quest discusses what's been accomplished since last spring's launch and what is on the horizon.
A game changer takes on cricket’s statistical problem
Laboratory for Information and Decision Systems alumnus and CSAIL lecturer Jehangir Amjad uses statistical methods to predict likely outcomes with limited data.
Creating 3-D-printed “motion sculptures” from 2-D videos
CSAIL system could help athletes, dancers, and others better analyze how they move.
Anant Agarwal, MIT professor and edX CEO, wins Yidan Prize
Agarwal is recognized for making education more accessible to people around the world, via edX open-source online platform.
Machine-learning system tackles speech and object recognition, all at once
Model learns to pick out objects within an image, using spoken descriptions.
Helping computers fill in the gaps between video frames
Machine learning system efficiently recognizes activities by observing how objects change in only a few key frames.
Robots can now pick up any object after inspecting it
Breakthrough CSAIL system suggests robots could one day be able to see well enough to be useful in people’s homes and offices.
Model can more naturally detect depression in conversations
Neural network learns speech patterns that predict depression in clinical interviews.
Model improves prediction of mortality risk in ICU patients
By training on patients grouped by health status, neural network can better estimate if patients will die in the hospital.
MIT-created programming language Julia 1.0 debuts
The dynamic programming language, which is free and open source, combines the speed and popular features of the best scientific and technical software.