MIT researchers are discovering which parts of the brain are engaged when a person evaluates a computer program.
Researchers found that the brain's multiple demand and language systems — which are responsible for very different cognitive tasks — encode specific code properties and uniquely align with machine-learned representations of code.Image: Alex Shipps/Canva
In a paper presented at NeurIPS, MIT researchers described their analysis to determine whether ML models trained on code corpora learn the same information that our brains learn when we comprehend code. Authors include Shashank Srikant and Benjamin Lipkin (lead authors), Anna Ivanova, Evelina Fedorenko, and Una-May O’Reilly.
This project was funded by grants from the MIT-IBM Watson AI lab, MIT Quest for Intelligence, National Science Foundation, National Institutes of Health, McGovern Institute for Brain Research, MIT Department of Brain and Cognitive Sciences, and the Simons Center for the Social Brain.