DCL Seminar Series: Tara Javidi

Active Hypothesis Testing for Information Acquisition and Active Learning

Contact
No contact information submitted.
Sidebar Content
No sidebar content submitted.
Summaries

Summary Sentence:

Active Hypothesis Testing for Information Acquisition and Active Learning

Full Summary:

Active Hypothesis Testing for Information Acquisition and Active Learning

Media
  • Tara Javidi Tara Javidi
    (image/jpeg)

Title:

Active Hypothesis Testing for Information Acquisition and Active Learning

 

Abstract:

In the first part of the talk, I will discuss an overview of my research on information acquisition and active learning in the context of the mission of our newly formed UCSD Center for Machine-Integrated Computing and Security (MICS). I will report of ongoing research on characterizing rate-reliability trade-off in active hypothesis testing, and hence bringing action into information theory and  Machine Learning. In the second part of the talk, I will delve deeper into  the problems of information acquisition, controlled sensing, and active learning and show our solutions to significantly reduce the cost of data collection and/or data labeling while ensuring reliability and fidelity during the training or run-time. In particular, we illustrate our findings and algorithms in the context of DetecDrone: an ML-enabled drone intelligence platform developed in my lab to provide search, mapping, and monitoring on off-the-shelf low cost drones. 

 

Bio: Tara Javidi received his BS in Electrical Engineering from Sharif University of Technology in 1996. She received her MS degrees in electrical engineering  and computer science (systems) and in applied mathematics (stochastic analysis) and her Ph.D. in electrical engineering and computer science from the University of Michigan, Ann Arbor. She is  currently a professor of electrical and computer engineering at the University of California, San Diego, where she is a founding co-director of the Center for Machine-aware Computing and Security (MICS). She is also a member of Board of Governors of the IEEE Information Theory Society (2017/18/19).

 

Tara Javidi’s research interests are in theory of active learning, information theory with feedback, stochastic control theory, and stochastic resource allocation in wireless communications and communication networks. Tara Javidi was a recipient of a 2018 Qualcomm Faculty Award, National Science Foundation early career award (CAREER) in 2004, Barbour Graduate Scholarship, University of Michigan, in 1999, and the Presidential and Ministerial Recognitions for Excellence in the National Entrance Exam, Iran, in 1992. Tara Javidi is a Distinguished Lecturer of the IEEE Information Theory Society (2017/18). 

Additional Information

Groups

Decision and Control Lab (DCL)

Categories
No categories were selected.
Related Core Research Areas
No core research areas were selected.
Newsroom Topics
No newsroom topics were selected.
Keywords
DCL Seminar Series
Status
  • Created By: mamstutz3
  • Workflow Status: Published
  • Created On: Dec 7, 2018 - 3:46pm
  • Last Updated: Dec 7, 2018 - 3:47pm