学术报告-From Mozi to Deep Learning and Beyond

主讲人简介:

Monson Hayes is Professor and Chair of the Department of Electrical and Computer Engineering at George Mason University in Fairfax, Virginia. Dr. Hayes was a Professor of Electrical and Computer Engineering at the Georgia Institute of Technology (1981-2011), and served as an Associate Chair in the School of ECE at Georgia Tech, and as Associate Director for Georgia Tech Savannah. Dr. Hayes is currently Professor Emeritus at Georgia Tech.

Dr. Hayes has served the Signal Processing Society of the IEEE in numerous positions, including Chairman of the DSP Technical Committee, Associate Editor for the IEEE Transactions on Acoustics, Speech, and Signal Processing and the IEEE Transactions on Education, SecretaryTreasurer of the ASSP Publications Board, and Chairman of the ASSP Publications Board, General Chairman of ICASSP 96, ICIP 2006 and ICASSP2018.

Dr. Hayes has published over 200 papers, is the author of two textbooks, and has received numerous awards and distinctions from professional societies as well as from Georgia Tech. His research interests are in the areas of digital signal processing, image and video processing, adaptive signal processing, pattern recognition and machine learning. Dr. Hayes is a Life Fellow of the IEEE.


座摘要:

Today we are in an age of zeros and ones, and it is often said that we are now living in a “DigitalUniverse.” Much of the digital data that we interact with daily is captured by cameras in the formof images and video, and a tremendous amount of research is being done on how to process,analyze, describe, search, catalog, compress, transmit and store this data. Fundamental research in image and video processing has evolved from problems having a primary focus that may be described as algorithmic, processing bytes of data on relatively small data sets, to research that is becoming increasingly more analytic, focusing on understanding and description, and computational, working on problems that involve massive amounts of data.

This talk begins with a brief historical perspective of the field of image processing that includes snapshots of the research problems that challenged the research community up to the point that the arrival of deep learning algorithms that now allow one to perform some truly amazing image processing tasks. The talk then branches into a more general discussion of the impact that machine learning has had in a vast array of applications. This talk is non-technical and should be appreciated by anyone in the field of engineering or science.


讲座地点:1号学院楼140

讲座时间:612 14:00