How well do explanation methods for machine-learning models work?
Researchers develop a way to test whether popular methods for understanding machine-learning models are working correctly.
Search Stories
“Hey, Alexa! Are you trustworthy?”
The more social behaviors a voice-user interface exhibits, the more likely people are to trust it, engage with it, and consider it to be competent.
Synthesis too slow? Let this robot do it.
Tiny Tides is an automated fast-flow instrument that can synthesize peptide-nucleic acids in a single shot.
Exploring growth within a confined space
Embedding bacteria in soft material tests researchers’ theories.
Meet the 2021-22 Accenture Fellows
The 2021-22 Accenture Fellows are bolstering research and igniting ideas to help transform global business.
Speeding up directed evolution of molecules in the lab
Using a new robotic platform, researchers can simultaneously track hundreds of microbial populations as they evolve new proteins or other molecules.
Scientists build new atlas of ocean’s oxygen-starved waters
The 3D maps may help researchers track and predict the ocean’s response to climate change.
Q&A: Cathy Wu on developing algorithms to safely integrate robots into our world
Assistant professor of civil engineering describes her career in robotics as well as challenges and promises of human-robot interactions.
Giving bug-like bots a boost
A new fabrication technique produces low-voltage, power-dense artificial muscles that improve the performance of flying microrobots.
From counting blood cells to motion capture, sensors drive patient-centered research
SENSE.nano symposium highlights the importance of sensing technologies in medical studies.
From “cheetah-noids” to humanoids
Benjamin Katz '16, SM '18 is applying the skills he gained working on MIT's mini cheetah robot to the ATLAS project at Boston Dynamics.
Machine learning speeds up vehicle routing
Strategy accelerates the best algorithmic solvers for large sets of cities.
Tiny machine learning design alleviates a bottleneck in memory usage on internet-of-things devices
New technique applied to small computer chips enables efficient vision and detection algorithms without internet connectivity.
Meet the Oystamaran
Working directly with oyster farmers, MIT students are developing a robot that can flip heavy, floating bags of oysters, helping the shellfish to grow and stay healthy.
Machines that see the world more like humans do
A new “common-sense” approach to computer vision enables artificial intelligence that interprets scenes more accurately than other systems do.