John Guttag earned an A.B. in English and an M.S. in Applied Mathematics from Brown University and a PhD in Computer Science from the University of Toronto. In 1999, Guttag served as the Head of MIT’s Electrical Engineering and Computer Science Department and as the Associate Department Head for Computer Science. Currently, Guttag co-heads MIT Computer Science and Artificial Intelligence Laboratory’s (CSAIL) Networks and Mobile Systems Group. In addition, Guttag has done research, published, and lectured in the areas of software engineering, mechanical theorem proving, hardware verification, compilation, and software radios. Some of his awards include: Board of Directors of Empirix, Inc., Board of Trustees of the MGH Institute of Health Professions, member of the American Academy of Arts and Sciences, and a fellow of the ACM.
Recent Works
Detecting Voice Misuse to Diagnose Disorders
This research focuses on using technology to help detect vocal misuse, patterns, and pathologies. With the help of collecting accelerometer data from a wearable device worn around the neck, developed by researchers at the MGH Voice Center. This learning algorithm examines which vocal cord movements are prominent in subjects with disorders, using unsupervised learning, where data is unlabeled at the instance level. By analyzing more than 110 million “glottal pulses” and comparing clusters of pulses, we detected significant differences between patients and controls.
Hidden Influencers, Risk and Causes of Infection
When modeling the spread of an infection among members or nodes of a community, each node’s probability of getting infected depends on its innate susceptibility and its exposure to the contagion through its neighbors (such as asymptomatic). This study investigates the causes and transmission modes of infectious diseases among members of a community in the presence of hidden, asymptomatic spreaders of the pathogen.
Machine Learning for Insights in Basketball Strategy
The player-tracking data for basketball are rich and spatiotemporal in extracting statistics, engineering, machine learning, and other methods that handle data. The aim is to supervise machine learning models to help understand the relationship between the players’ movement (on offense) and calculate successful outcomes like quality shots. With the help of deep learning models (CNNs) to uncover features about the players’ movement that is relative to the offensive success. These models can provide insightful information that involves offensive strategy in basketball or the players’ evaluation metrics.