Keynote Speakers

Prof. 

Chong-Yung Chi

Bio: 

Chong-Yung Chi (IEEE Life Fellow, AAIA & AIIA Fellows, NAAI Member) received a B.S. degree from Tatung Institute of Technology, Taipei, Taiwan, in 1975, an M.S. degree from National Taiwan University, Taipei, Taiwan, in 1977, and a Ph.D. degree from the University of Southern California, Los Angeles, CA, USA, in 1983, all in electrical engineering.

He is a Professor at National Tsing Hua University, Hsinchu, Taiwan. He has published more than 240 technical papers (with citations more than 8200 times by Google-Scholar), including more than 100 journal papers (mainly in IEEE TRANSACTIONS ON SIGNAL PROCESSING), more than 140 peer-reviewed conference papers, 3 book chapters, and 2 books, including a textbook, Convex Optimization for Signal Processing and Communications: From Fundamentals to Applications, CRC Press, 2017 (which has been popularly used in a series of invited intensive short courses at 10 top-ranking universities in Mainland China since 2010 before its publication). His research interests include signal processing for wireless communications, convex analysis and optimization for blind source separation, biomedical and hyperspectral image analysis, graph-based learning and signal processing, and data security and privacy protection in machine learning. 

Title: CVXopt-Aided AI for Unsupervised HSI Denoising and Super-Resolution 

Abstract: 

Convex optimization (CVXopt), has been extensively applied in sciences and engineering over the last decades. Artificial Intelligence (AI), such as Machine Learning (ML) and Deep Learning (DL), has been pervasive not only in sciences and engineering but also in our daily lives. A specific mathematical model and problem formulation are required for the former, while free from any pretraining; meanwhile, optimal or acceptable approximate solutions can always be obtained, together with insightful performance characteristics and unique properties that may be disclosed and used as the guidelines for practical algorithm implementation and development. A big training dataset and tremendous computing costs are frequently required for the latter, thanks to neither a math model nor intricate mathematics; hence, a tractable performance/convergence analysis is essential but still a bottleneck. In this speech, we will address their intriguing fusion (termed CVXopt-aided AI), which demonstrates fantastic learning performance via the following deep image prior (DIP) based AI application instances:

1. DIP-based Unsupervised Hyperspectral Image (HSI) Denoising:  The sparse noise is detected and suppressed by CVXopt, and then the ground truth is recovered using a DIP (a convolutional neural network).  
    2. DIP-based Unsupervised HSI Super-Resolution (HSI-SR): After suppressing the sparse noise by CVXopt, two coupled DIPs (with identical architecture) in parallel are used to capture the utmost essential spectral (spatial) features from a low (high) spatial resolution HSI X (multispectral Y) and guide the generation of abundance tensor G and spectral signature matrix E, respectively, finally yielding the desired tensor HSI-SR Z from G and E.