Using Machine Learning to Study How Brains Represent Language Meaning
Dr. Tom M. Mitchell
E. Fredkin University Professor, Machine Learning Department, School of Computer Science, Carnegie Mellon University
Presentation of the President's Medal to Dr. Mitchell immediately following the President's Distinguished Lecture
Event registration is at capacity. Guests are asked to arrive 30 minutes early to secure seating in DeBaun Auditorium. Registration does not guarantee admission. Ticketed guests will be seated on a first-come, first-served basis. For those unable to secure seating, the lecture will be streamed live in a separate location in Edwin A. Stevens Hall and a high-definition video will be posted at stevens.edu/lecture following the event.
ABSTRACT: How does the human brain use neural activity to create and represent meanings of words, phrases, sentences and stories? One way to study this question is to give people text to read while scanning their brain. At Carnegie Mellon University, researchers in the machine learning department have been conducting such experiments with fMRI (1 mm spatial resolution) and MEG (1 msec time resolution) brain imaging, and developing novel machine learning approaches to analyzing this data. These experiments are producing answers to questions such as:
- "Are the neural encodings of word meaning the same in your brain and that of another?"
- "Are neural encodings of word meaning built out of recognizable subcomponents, or are they randomly different for each word?,"
- "What sequence of neurally encoded information flows through the brain during the half-second in which the brain comprehends a word?,"
- “How are meanings of multiple words combined when reading phrases, sentences, and stories?”
This talk will summarize Carnegie Mellon’s machine learning approach, what has been learned, and newer questions that are currently being studied.
BIOGRAPHY: Dr. Tom M. Mitchell is the E. Fredkin University Professor at Carnegie Mellon University, where he founded the world's first machine learning department. His research uses machine learning to develop computers that are learning to read the web and uses brain imaging to study how the human brain understands what it reads. He co-chaired the 2017 U.S. National Academy study on “Information Technology, Automation, and the U.S. Workforce,” and has testified before the U.S. Congressional Research Service and the U.S. House Subcommittee on Veterans' Affairs on the potential uses and impacts of artificial intelligence. Dr. Mitchell is a member of the U.S. National Academy of Engineering, the American Academy of Arts and Sciences, and a Fellow and past president of the Association for the Advancement of Artificial Intelligence (AAAI). For more information on Professor Mitchell’s research, please visit http://rtw.ml.cmu.edu.
ATTENDANCE: This event is open to all Stevens students, faculty, staff, alumni, and invited guests. Tickets will be emailed the week of the event.
Seating limited. Registration required. Reception to follow in Babbio Atrium.