2015/7/16(四)14:20 - Prof. Yih-Fang Huang (University of Notre Dame) - Diffusion Distributed Adaptive Estimation
講 題：Diffusion Distributed Adaptive Estimation
演講者：Prof. Yih-Fang Huang (University of Notre Dame)
時 間：2015年7月16日(星期四)下午2:30~4:00
地 點：台達館919室
ABSTRACT:
This talk presents diffusion-based approaches to distributed adaptive estimation and filtering. In the diffusion distributed adaptive estimation paradigm, the nodes generate their estimates by fusing the intermediate estimates of their neighboring nodes, rendering more robust estimates with respect to link or node failures. In reality, diffusion may not always be needed. If we can be more discerning on when and what to diffuse, with performance guarantees, the resulting adaptive network will be more resource-efficient. This talk examines various mechanisms that can save on the overhead of diffusion without significantly compromising the system performance.
BIOGRAPHY:
Yih-Fang Huang is Professor of Department of Electrical Engineering and Senior Associate Dean of College of Engineering at University of Notre Dame. Dr. Huang received his BSEE degree from National Taiwan University, MSEE degree from University of Notre Dame and MA and Ph.D. from Princeton University. He served as chair of the Electrical Engineering Department at the University of Notre Dame from 1998 to 2006. His research interests focus on theory and applications of statistical signal processing and adaptive filters.
演講者：Prof. Yih-Fang Huang (University of Notre Dame)
時 間：2015年7月16日(星期四)下午2:30~4:00
地 點：台達館919室
ABSTRACT:
This talk presents diffusion-based approaches to distributed adaptive estimation and filtering. In the diffusion distributed adaptive estimation paradigm, the nodes generate their estimates by fusing the intermediate estimates of their neighboring nodes, rendering more robust estimates with respect to link or node failures. In reality, diffusion may not always be needed. If we can be more discerning on when and what to diffuse, with performance guarantees, the resulting adaptive network will be more resource-efficient. This talk examines various mechanisms that can save on the overhead of diffusion without significantly compromising the system performance.
BIOGRAPHY:
Yih-Fang Huang is Professor of Department of Electrical Engineering and Senior Associate Dean of College of Engineering at University of Notre Dame. Dr. Huang received his BSEE degree from National Taiwan University, MSEE degree from University of Notre Dame and MA and Ph.D. from Princeton University. He served as chair of the Electrical Engineering Department at the University of Notre Dame from 1998 to 2006. His research interests focus on theory and applications of statistical signal processing and adaptive filters.