M
Michael C. Mozer
Researcher at Google
Publications - 251
Citations - 12247
Michael C. Mozer is an academic researcher from Google. The author has contributed to research in topics: Artificial neural network & Deep learning. The author has an hindex of 54, co-authored 235 publications receiving 10752 citations. Previous affiliations of Michael C. Mozer include University of Pittsburgh & University of Colorado Boulder.
Papers
More filters
Journal ArticleDOI
Bayesian community-wide culture-independent microbial source tracking
Dan Knights,Justin Kuczynski,Emily S. Charlson,Jesse R. Zaneveld,Michael C. Mozer,Ronald G. Collman,Frederic D. Bushman,Rob Knight,Rob Knight,Scott T. Kelley +9 more
TL;DR: SourceTracker, a Bayesian approach to estimate the proportion of contaminants in a given community that come from possible source environments, is presented, and microbial surveys from neonatal intensive care units, offices and molecular biology laboratories are applied.
The Neural Network House: An Environment that Adapts to its Inhabitants
TL;DR: In this article, the authors describe an approach for the home to essentially program itself by observing the lifestyle and desires of the inhabitants, and learning to anticipate and accommodate their needs, and demonstrate a prototype system in an actual residence and describe initial results and the current state of the project.
Skeletonization: A Technique for Trimming the Fat from a Network via Relevance Assessment ; CU-CS-421-89
Michael C. Mozer,Paul Smolensky +1 more
TL;DR: The basic idea is to iteratively train the network to a certain performance criterion, compute a measure of relevance that identifies which input or hidden units are most critical to performance, and automatically trim the least relevant units.
Proceedings Article
Skeletonization: A Technique for Trimming the Fat from a Network via Relevance Assessment
Michael C. Mozer,Paul Smolensky +1 more
TL;DR: In this paper, the authors propose a means of using the knowledge in a network to determine the functionality or relevance of individual units, both for the purpose of understanding the network's behavior and improving its performance.
Journal ArticleDOI
Deep neural network improves fracture detection by clinicians.
Robert V. Lindsey,Aaron Daluiski,Sumit Chopra,Alexander Lachapelle,Michael C. Mozer,Serge Sicular,Douglas P. Hanel,Michael J. Gardner,Anurag Gupta,Robert N. Hotchkiss,Hollis G. Potter +10 more
TL;DR: The significant improvements in diagnostic accuracy that are observed in this study show that deep learning methods are a mechanism by which senior medical specialists can deliver their expertise to generalists on the front lines of medicine, thereby providing substantial improvements to patient care.