<span class="vcard">Larry Hardesty | MIT News Office</span>
Larry Hardesty | MIT News Office

Making driverless cars change lanes more like human drivers do

Algorithm computes “buffer zones” around autonomous vehicles and reassess them on the fly.

Computer system transcribes words users “speak silently”

Electrodes on the face and jaw pick up otherwise undetectable neuromuscular signals triggered by internal verbalizations.

Computer searches telescope data for evidence of distant planets

Machine-learning system uses physics principles to augment data from NASA crowdsourcing project.

Neural networks everywhere

New chip reduces neural networks’ power consumption by up to 95 percent, making them practical for battery-powered devices.

Study finds gender and skin-type bias in commercial artificial-intelligence systems

Examination of facial-analysis software shows error rate of 0.8 percent for light-skinned men, 34.7 percent for dark-skinned women.

3Q: D. Fox Harrell on his video game for the #MeToo era

The computer scientist’s group has designed a game that gets players to reflect on sexual misconduct in the workplace.

Can computers help us synthesize new materials?

Machine-learning system finds patterns in materials “recipes,” even when training data is lacking.

Computer systems predict objects’ responses to physical forces

Results may help explain how humans do the same thing.

Reading a neural network’s mind

Technique illuminates the inner workings of artificial-intelligence systems that process language.

Try this! Researchers devise better recommendation algorithm

Improved recommendation algorithm should work especially well when ratings data are “sparse.”