
Hi, I’m Jaesung Yoo. I am currently a visiting research assistant at Metaconscious Lab, MIT. I previously worked at Biomedical Informatics Lab, Seoul National University Hospital, working on continual learning, AI in medical neuroscience, and privacy-preserving deep learning.
Research Interests
- Developing neural network models for biomedicine
- Explainable deep neural networks & Neural networks as computational neuroscience model
- Synaptic plasticity and learning algorithms for deep neural networks
Publications
(*equal contributions)
Jaesung Yoo*, Ilhan Yoo*, Ina Youn, Sung-Min Kim, Ri Yu, Kwangsoo Kim, Keewon Kim, Seung-Bo Lee. Residual one-dimensional convolutional neural network for neuromuscular disorder classification from needle electromyography signals with explainability. Computer Methods and Programs in Biomedicine (2022). https://doi.org/10.1016/j.cmpb.2022.107079
(Under review)
Jaesung Yoo, Sunghyouk Choi, Ye Seul Yang, Suhyeon Kim, Jieun Choi, Dongkyeong Lim, Yaeji Lim, Hyung Joon Joo, Dae Jung Kim, Rae Woong Park, Hyeong-Jin Yoon, Kwangsoo Kim. Review learning: Alleviating catastrophic forgetting with generative replay without a generator. https://arxiv.org/abs/2210.09394
Ilhan Yoo*, Jaesung Yoo*, Dongmin Kim, Ina Youn, Hyodong Kim, Michelle Youn, Jun Hee Won, Woosup Cho, Youho Myong, Sehoon Kim, Ri Yu, Sung-Min Kim, Kwangsoo Kim, Seung-Bo Lee, Keewon Kim. Deep learning model for needle electromyography electrodiagnosis in comparison with physician assessment: A retrospective study. https://doi.org/10.1101/2023.01.13.23284511
Jaesung Yoo*, Sunghyouk Choi*, Suhwan Kim, Joongheon Kim, Kwangsoo Kim, Hyung-Jin Yoon. Transfer iterative learning in privacy preserving deep learning: a common data model study
Skills
Enjoy teaching & tutoring. Give easy explanations.
I code succinctly and intuitively.
Personal syntax tools, Personal deep learning toolkit for python available in PyPI.
Native in Korean, English and Python.
Learning Chinese, Japanese, and Spanish.
Warm hearted, Optimistic.