Explained: How to tell if artificial intelligence is working the way we want it to

“Interpretability methods” seek to shed light on how machine-learning models make predictions, but researchers say to proceed with caution.

Adam Zewe | MIT News Office • mit
July 22, 2022 ~11 min

Explained: Detecting the threat of nuclear weapons | MIT News

Professor of nuclear science and engineering Scott Kemp describes the science behind the search for clandestine nuclear sites.

Meg Murphy | School of Engineering • mit
June 8, 2018 ~8 min


Explained: Neural networks | MIT News

Ballyhooed artificial-intelligence technique known as “deep learning” revives 70-year-old idea.

Larry Hardesty | MIT News Office • mit
April 14, 2017 ~10 min

Explained: Greenhouse gases | MIT News

Carbon dioxide isn’t the only one that matters, and the gases vary widely in potency and duration.

David L. Chandler | MIT News Office • mit
Jan. 30, 2017 ~9 min

Explained: chemical vapor deposition | MIT News

Technique enables production of pure, uniform coatings of metals or polymers, even on contoured surfaces.

David L. Chandler | MIT News Office • mit
June 19, 2015 ~6 min

/

1