Marina Mancoridis

I am a third-year Computer Science PhD student at MIT, advised by Sendhil Mullainathan in the MIT Bike Shop.

I think about problems at the intersection of machine learning and the measurement of understanding. Recently, I have been building evaluations which (1) test whether benchmark performance reflects true or ‘Potemkin’ concept understanding, (2) probe how humans and models structure concepts through consistency and analogical tests, and (3) study these questions in strategic games like poker, where gameplay under imperfect information may be improved by psychological models of an opponent.

Before MIT, I graduated summa cum laude from Princeton University with a degree in Computer Science. At Princeton, I worked with Tom Griffiths in the Computational Cognitive Science Lab. Upon graduating, I received the Calvin Dodd MacCracken Senior Thesis Award for the most inventive and technically accomplished senior thesis in the School of Engineering and Applied Sciences.