Data diversity
Preserving variety in subsets of unmanageably large data sets should aid machine learning.
Making big data manageable
Technique shrinks data sets while preserving their fundamental mathematical relationships.
Learning words from pictures
System correlates recorded speech with images, could lead to fully automated speech recognition.
Design your own custom drone
CSAIL system lets users design and fabricate drones with a wide range of shapes and structures.
Creating videos of the future
Given a still image, CSAIL deep-learning system generates videos that predict what will happen next in a scene.
Faster programs, easier programming
New system lets nonexperts optimize programs that run on multiprocessor chips.
Finding patterns in corrupted data
New model-fitting technique is efficient even for data sets with hundreds of variables.
Quantifying urban revitalization
Combining cellphone data with perceptions of public spaces could help guide urban planning.
MRIs for fetal health
Algorithm could help analyze fetal scans to determine whether interventions are warranted.
With new model, buildings may “sense” internal damage
System predicts how MIT’s tallest structure responds to vibrations, may help monitor stress over time.
Algorithm connects students to the most interesting person they’ve never met
Tuka Al-Hanai and Mohammad Ghassemi have connected over 500 MIT students for more than 1,000 lunch meetings.
Q&A: How Twitter explains the 2016 election
“Electome” project charts the national conversation in unique detail.
Cache management improved once again
New version of breakthrough memory management scheme better accommodates commercial chips.