Seongwon (Gabriel) Yoon

I completed my degree from Seoul National University with B.S. in materials science in engineering, Summa Cum laude, ranked 4th in class of 2022.

I worked as a software engineer at Imagoworks Inc., a KIST spinoff deep learning company, where I was involved in the compilation of quality data and fine-tuning of generative models.

From 2019 to present, I am working under the guidance of Mr. Masatoshi Ishii (IBM Research-Tokyo) and Prof. Sangbum Kim (Seoul National University) as a student researcher for neuromorphic chip hardware-aware simulator development and solve combinatorial optimization problems under the IBM-SNU Joint-Study Agreement.

From the summer of 2023, I am working under the guidance of Prof. Hyung-Min Lee (Korea University) and Prof. Sangbum Kim (Seoul National University) for on-chip training of IGZO TFT capacitor-based synapse array.

From Fall 2024, I am a Georgia Tech ECE Ph.D. student in Prof. Shimeng Yu's Laboratory for Emerging Devices and Circuits . I am currently involved in in-pixel circuit design of CMOS image sensor.

Email  /  Resume  /  Github

profile photo

Research

My research interests include software-hardware co-design for neuro-inspired computing and AI hardware design, with a particular focus on training and inference accelerators.

Solving Max-Cut Problem using Boltzmann Machine based on Phase Change Memory
Yu Gyeong Kang, Masatoshi Ishii, Jaeweon Park, Uicheol Shin, Suyeon Jang, Seongwon Yoon, Mingi Kim, Atsuya Okazaki, Megumi Ito, Akiyo Nomura, Kohji Hosokawa, Matthew Brightsky, Sangbum Kim
In revision in Advanced Science(), Aug 2024.

Max-Cut problem solver using the IBM neuromorphic chip (phase-change material GST based non-volatile memory synapse) hardware-aware simulator

Clinical validity and precision of deep learning-based Cone-Beam Computed Tomography automatic landmarking algorithm
Jungeun Park, Seongwon Yoon, Hannah Kim, Youngjun Kim, Woncheul Choi, Young Jun Choi, Hyungseog Yu, Uilyong Lee
Imaging Science in Dentistry (), 2024.

Aimed to evaluate the clinical validity and accuracy of a deep learning-based cone-beam computed tomography (CBCT) automatic landmarking algorithm by comparing three dimensional CBCT head measurement values obtained by manual and automatic landmarking. This study further developed into the business solution CT Landmark Detection

Solving Constraint Satisfaction Problem with Spiking Neural Network based on 1.4M 6T2R PCM Synaptic Array with 1.6K Stochastic LIF Neurons Neuromorphic Hardware
Seongwon Yoon, Uicheol Shin, Sangbum Kim
The 28th Korean Conference on Semiconductors (KCS), 2021.

Traveling Salesman Problem (TSP) solver based on the IBM neuromorphic chip (phase-change material GST based non-volatile memory synapse) hardware-aware simulator [code]

Ongoing Project
On-Chip Training of Capacitor-Based Synaptic Device with IGZO TFT Deep Neural Network
Seongwon Yoon, Jongwoon Won, Jaehyun Kang, Hyung-Min Lee, Sangbum Kim
(), 2023.

On-chip training of 5x5 synapse array with parallel update method using conventional stochastic gradient descent and backpropagation to solve XOR problem. [code]


Design and source code from Jon Barron Website.