D
David Petrou
Researcher at Google
Publications - 82
Citations - 4570
David Petrou is an academic researcher from Google. The author has contributed to research in topics: Mobile device & Web search query. The author has an hindex of 27, co-authored 81 publications receiving 3889 citations. Previous affiliations of David Petrou include Carnegie Mellon University.
Papers
More filters
Posted Content
Towards Federated Learning at Scale: System Design
Keith Bonawitz,Hubert Eichner,Wolfgang Grieskamp,Dzmitry Huba,Alex Ingerman,Vladimir Ivanov,Chloe Kiddon,Jakub Konečný,Stefano Mazzocchi,H. Brendan McMahan,Timon Van Overveldt,David Petrou,Daniel Ramage,Jason Roselander +13 more
TL;DR: In this paper, a scalable production system for federated learning in the domain of mobile devices, based on TensorFlow, is presented. Butler et al. describe the resulting high-level design, sketch some of the challenges and their solutions, and touch upon the open problems and future directions.
Towards Federated Learning at Scale: System Design
Keith Bonawitz,Hubert Eichner,Wolfgang Grieskamp,Dzmitry Huba,Alex Ingerman,Vladimir Ivanov,Chloe Kiddon,Jakub Konečný,Stefano Mazzocchi,H. Brendan McMahan,Timon Van Overveldt,David Petrou,Daniel Ramage,Jason Roselander +13 more
TL;DR: A scalable production system for Federated Learning in the domain of mobile devices, based on TensorFlow is built, describing the resulting high-level design, and sketch some of the challenges and their solutions.
Patent
Facial recognition with social network aiding
TL;DR: In this paper, a facial recognition search system identifies one or more likely names (or other personal identifiers) corresponding to the facial image(s) in a query as follows: after receiving the visual query with one or multiple facial images, the system identifies images that potentially match the respective facial image in accordance with visual similarity criteria.
Patent
Query-independent entity importance in books
TL;DR: In this paper, an entity importance engine analyzes the information in the corpus to identify the entities mentioned therein, and ranks the entities using query-independent importance scores, based on the contexts in which the entities are mentioned by the books.
Patent
Architecture for responding to a visual query
TL;DR: In this article, a visual query such as a photograph, a screen shot, a scanned image, a video frame, or an image created by a content authoring application is submitted to a VQS system.