Unpacking black-box models
Researchers create a mathematical framework to evaluate explanations of machine-learning models and quantify how well people understand them.
Download RSS feed: News Articles / In the Media / Audio
Researchers create a mathematical framework to evaluate explanations of machine-learning models and quantify how well people understand them.
A new machine-learning system may someday help driverless cars predict the next moves of nearby drivers, cyclists, and pedestrians in real-time.
A multidisciplinary team of graduate students helps infuse ethical computing content into MIT’s largest machine learning course.
A new robotic manipulation course provides a broad survey of state-of-the-art robotics, equipping students to identify and solve the field’s biggest problems.
Faculty leaders highlight innovations that can close longstanding knowledge gaps and reimagine how the world responds to the climate crisis.
The Institute also ranks second in two subject areas.
MIT scientists hope to deploy a fleet of drones to get a better sense of how much carbon the ocean is absorbing, and how much more it can take.
MIT researchers design a robot that has a trick or two up its sleeve.
As he works toward a career in aerospace engineering, senior Devin Johnson uplifts others along the way.
Graduate engineering, economics, and various science programs are No. 1 in the nation; MIT Sloan is No. 5.
Faculty leaders detail promising technologies, materials, and methods that could help unlock a low-carbon future in sectors where emissions are hardest to cut.
Veteran and PhD student Andrea Henshall has used MIT Open Learning to soar from the Air Force to multiple aeronautics degrees.
In collaboration with industry representatives, Momentum students tackle wildfire suppression and search-and-rescue missions while building soft skills.
The computer-vision technique behind these maps could help avoid contrail production, reducing aviation’s climate impact.
Faculty leaders discuss the opportunities and obstacles in developing, scaling, and implementing their work rapidly.