Machine-Integrated Intelligence, Controlled Sensing, and Active Learning

ABSTRACT: The computing landscape has been drastically changing. The new computing realm, which is sometimes dubbed as internet of everything, includes networked devices ranging from tiny wearable sensors, smart home appliances, and personal autonomous robots, to connected self-driving cars, and to smart city infrastructures. In this new computing eco-system, comprising of resource-constrained, unreliable, and vulnerable components and networks, the non-recurring cost of hardware acceleration, engineering implementation, and system building has continued to grow significantly. This is in addition to the growing cost associated with the collection, curation, and labeling of data during both the training and the execution of various popular machine learning models. These design bottle-necks not only result in a significant increase in the non-recurring cost of engineering for companies, but also provide a severe hurdle in technology development associated with hardware upgrade and/or system redesign.

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 in the center where this system integrated view has enabled best-in-class results by bringing Machine into 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 studied electrical engineering at Sharif University of Technology, Tehran, Iran from 1992 to 1996. She received her MS degrees in electrical engineering (systems) and in applied mathematics (stochastic analysis) from the University of Michigan, Ann Arbor, in 1998 and 1999, respectively. She received her Ph.D. in electrical engineering and computer science from the University of Michigan, Ann Arbor, in 2002. From 2002 to 2004, Tara Javidi was an assistant professor at the Electrical Engineering Department, University of Washington, Seattle. In 2005, she joined the University of California, San Diego, where she is currently a professor of electrical and computer engineering and 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).

Hosted by: Paul Bogdan