J
Johnson T. Apacible
Researcher at Microsoft
Publications - 77
Citations - 5707
Johnson T. Apacible is an academic researcher from Microsoft. The author has contributed to research in topics: Context (language use) & Web search query. The author has an hindex of 32, co-authored 77 publications receiving 5603 citations.
Papers
More filters
Proceedings ArticleDOI
Project Adam: building an efficient and scalable deep learning training system
TL;DR: The design and implementation of a distributed system called Adam comprised of commodity server machines to train large deep neural network models that exhibits world-class performance, scaling and task accuracy on visual recognition tasks and shows that task accuracy improves with larger models.
Patent
Thematic response to a computer user's context, such as by a wearable personal computer
TL;DR: Themes can represent various types of contextual aspects or situations, and can model high-level concepts of activities or states not reflected in individual contextual attributes that each model a single aspect of the state of a user, their computing device, the surrounding physical environment, and/or the current cyber-environment as discussed by the authors.
Patent
Methods and architecture for cross-device activity monitoring, reasoning, and visualization for providing status and forecasts of a users' presence and availability
TL;DR: In this article, the authors present a system and methodology to facilitate collaboration and communications between entities such as between automated applications, parties to a communication and/or combinations thereof by learning predictive models that provide forecasts of one or more aspects of a users' presence and availability.
Patent
Harnessing information about the timing of a user's client-server interactions to enhance messaging and collaboration services
Eric Horvitz,Johnson T. Apacible +1 more
TL;DR: In this paper, a system and method is provided to facilitate communication and collaboration by considering the timing of a user's activities on one or more clients via accessing, from a centralized server, information about the user's client-server interactions.
Proceedings ArticleDOI
Learning and reasoning about interruption
Eric Horvitz,Johnson T. Apacible +1 more
TL;DR: Methods for inferring the cost of interrupting users based on multiple streams of events including information generated by interactions with computing devices, visual and acoustical analyses, and data drawn from online calendars are presented.