PI
Core/Dual

Antonio Torralba

Professor

Phone

324-0900

Room

/ 32-D462

Antonio Torralba is a Professor of Electrical Engineering and Computer Science at the Massachusetts Institute of Technology (MIT), the MIT director of the MIT-IBM Watson AI Lab, and the inaugural director of the MIT Quest for Intelligence, an MIT campus-wide initiative to discover the foundations of intelligence. He received the degree in telecommunications engineering from Telecom BCN, Spain in 1994 and the 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.

Projects

Project

Understanding Health Habits from Social Media Pictures

We focus on learning combined modalities (cooking recipes and food images), analyzing differences in how a machine would objectively label an image compared to how a human subjectively does, and estimating the population health level from social media images.

Amaia Salvador

Enes Kocabey

Mustafa Camurcu

+3

Ingmar Weber

Leads

Ingmar Weber

Research Areas

Project

Neural Physics Engine

We've developed an object-based neural network architecture for learning predictive models of intuitive physics that extrapolates to variable object count and variable scene configurations with only spatially and temporally local computation.
Torralba
Tenenbaum

Leads

Project

Understanding Light via Deep Neural Networks

Our goal is to understand the illumination of an environment. By disentangling the illumination effect from other intrinsic properties (e.g. geometry, texture, color), we can better understand how human perceive the world. It also has several applications such as single image relighting, color editing, etc.

 8 More

Groups

News

Learning words from pictures

Speech recognition systems, such as those that convert speech to text on cellphones, are generally the result of machine learning. A computer pores through thousands or even millions of audio files and their transcriptions, and learns which acoustic features correspond to which typed words.But transcribing recordings is costly, time-consuming work, which has limited speech recognition to a small subset of languages spoken in wealthy nations.