How to tell whether machine-learning systems are robust enough for the real world
New method quickly detects instances when neural networks make mistakes they shouldn’t.
New method quickly detects instances when neural networks make mistakes they shouldn’t.
In some cases, radio frequency signals may be more useful for caregivers than cameras or other data-collection methods.
MIT CSAIL project shows the neural nets we typically train contain smaller “subnetworks” that can learn just as well, and often faster.
Algorithm stitches multiple datasets into a single “panorama,” which could provide new insights for medical and biological studies.
Data-sampling method makes “sketches” of unwieldy biological datasets while still capturing the full diversity of cell types.
CSAIL team studies what email users want for better automating email — and proposes "YouPS" filtering tool.
In planning for the MIT Schwarzman College of Computing, working group is exploring needs across all parts of the Institute.
Researchers unveil a tool for making compressed deep learning models less vulnerable to attack.
Working group discussions focus on how to design the MIT Schwarzman College of Computing to best serve the community and society.
MIT researchers joined Cambridge Rindge and Latin School students for a two-day event focused on future-ready skills.
Working Group on Curricula and Degrees co-chairs discuss their progress toward establishing credentials and courses for the college.
EECS faculty member is recognized for technical innovation, educational excellence, and efforts to advance women and underrepresented minorities in her field.
Co-chairs of the Organizational Structure working group discuss their goals and progress.
Model improves a robot’s ability to mold materials into shapes and interact with liquids and solid objects.
CSAIL’s "RoCycle" system uses in-hand sensors to detect if an object is paper, metal or plastic.