Posts

Following three master’s students have joined SDLab. Welcome!

Mr. Wassapon Watanakeesuntorn and Mr. Kundjanasith Thonglek attended the “RIKEN International HPC Summer School 2020 - Toward Society 5.0 -" held by the RIKEN Center for Computational Science (R-CCS) from September 28 to 30, 2020.

Mr. Kundjanasith Thonglek has received his master’s degree in engineering. He will continue his research at SDLab and pursue his PhD. Congratulations!

Mr. Guoqing Li, an intern at SDLab, participated in the Google Summer of Code 2020 (GSoc 2020) program from June 1 to August 24, 2020, and officially completed it. Mr. Li contributed to the libvirt project (a library to manage diverse virtualization platforms through a unified API), and extended and improved the libvirt plugin for SaltStack. See here for an overview of his work and here for his final report.

Mr. Kundjanasith Thonglek, a master’s student at SDLab, presented his research to his thesis committee on August 24th, 2020.

Mr. Kundjanasith Thonglek presented the following paper at International Joint Conference on Neural Networks (IJCNN) of IEEE Word Congress on Computational Intelligence (WCCI) 2020. Kundjanasith Thonglek, Keichi Takahashi, Kohei Ichikawa, Chawanat Nakasan, Hidemoto Nakada, Ryousei Takano and Hajimu Iida, “Retraining Quantized Neural Network Models with Unlabeled Data”, International Joint Conference on Neural Networks (IJCNN 2020), Jul. 2020. In this paper, we focus on the fact that we cannot always access the original labeled datasets because of privacy policies and license limitations.

Mr. Guoqing Li, who has been staying at our lab as an internship student, presented his work on April 13, 2020. Mr. Li is an undergraduate student at Chiang Mai University, Thailand, and he has been working on a research internship at our lab since January this year. Mr. Li’s research topic is entitled “Comparative Performance Study of Cloud Native Hypervisors.” He conducted an extensive performance evaluation of emerging container runtimes and hypervisors that provide better isolation than conventional container runtimes.