Using Visual Noise, Not Human-Generated Labels, To Train AI

Using Visual Noise, Not Human-Generated Labels, To Train AI

Date Posted:  December 1, 2023
Date Recorded:  July 30, 2023
CBMM Speaker(s):  Antonio Torralba
  • All Captioned Videos
Associated CBMM Pages: 
Description: 

Antonio Torralba is a Delta Electronics Professor of Electrical Engineering and Computer Science at the Massachusetts Institute of Technology (MIT) and Head of the AI+D faculty in the EECS department. He received a degree in telecommunications engineering from Telecom BCN, Spain in 1994 and a Ph.D. degree in signal, image, and speech processing from the Institut National Polytechnique de Grenoble, France in 2000. From 2000 to 2005, he spent postdoctoral training at the Brain and Cognitive Sciences Department and the Computer Science and Artificial Intelligence Laboratory, MIT, where he is now a professor.

Part of CSAIL + Imagination in Action

CSAIL + Imagination in Action jointly hosted a landmark event in honor of CSAIL's 60-year anniversary. On Tuesday, June 27, experts and startup pioneers from across CSAIL shared inspiring talks and thought-provoking ideas. Our symposium aims to bridge the gap between groundbreaking AI innovations and practical applications, providing a platform for luminaries and startup pioneers within CSAIL's ecosystem to share their trailblazing insights and perspectives. Experts from our laboratory exchanged ideas as they delved into their visions for AI, highlighting exciting opportunities and addressing potential risks.