Last updated: 2020-05-28
I am a senior student majoring Electrical and Computer Engineering at Seoul National University, South Korea. I am interested in large-scale distributed computer systems that deal with deep learning workloads. I also try to follow up on state-of-the-art deep learning research during my free time. I seek to apply for a Ph.D. position in the U.S. in late 2020.
Check out my Résumé!
GPU cluster resource management
• Developing Crane, an elastic GPU cluster manager for deep learning workloads.
Distributed DNN inference, Mobile Computing
• Worked with Prof. Soo-Mook Moon on developing distributed DNN inference schemes. • Proposed a distributed video DNN inference scheme that drastically reduces network traffic by exploiting intermittent knowledge distillation. • Implemented the scheme with PyTorch and OpenMPI with an NVIDIA Jetson Nano embedded board as the client and conducted evaluation.
Meta-learning, Few-shot Classification• Conducted research on better meta-initialization points for Model-Agnostic Meta-Learning (MAML) using an LSTM-based neural memory. • Conducted research on generating task-aware class embeddings to augment feature maps of MAML by formulating a convex program (DPP).
Quantitative Susceptibility Mapping (QSM), Deep Learning• Worked with Prof. Jongho Lee to submit our solution to the QSM challenge held by the 5th Int'l Workshop on MRI Phase Contrast and QSM. • Designed, implemented, and trained a U-Net variant on in-vivo brain MRI field images and their COSMOS results.
A free research group on all domains of deep learning• Gained experience extensively in computer vision and meta-learning, and attended talks on computer vision, natural language processing, reinforcement learning, and speech recognition. • Gave a talk with the title "Memory plus Meta-Learning".
An official Coursera community that traslates Coursera lecture subtitles• Served as Language Coordinator, a selected position that reviews and confirms works by other translators. • Created Korean subtitles for Coursera Lectures initially provided only in English. Focused on courses related to machine learning.
Skills & Proficiency
MATLAB, HTML, JS, LaTeX
In ICPP (Acceptance Rate 29%=78/269), Edmonton, CA, 2020.