JISOO LEE
About

Hi, I finished the 10-month internship at KIXLAB (KAIST Interaction Lab), working with Prof. Juho Kim. Before joining KIXLAB, I was mainly interested in training deep neural networks with limited supervision such as noisy labels. I received my bachelor’s degree in Electrical Engineering (with a minor in Computing) from KAIST in 2017 and my master’s degree in Electrical Engineering from KAIST in 2019, working with Prof. Sae-Young Chung.

Here's my CV.
Research Interests

My research aims at building reliable systems through collaboration between humans and AI. To this end, I am studying machine/deep learning and human-computer interaction both. In particular, my research focus is on
(1) training neural networks with limited supervision
(2) causal inference to understand black-box properties of deep learning
(3) improving ML algorithm performance for a better user experience.
Publications

[C1] Robust training with ensemble consensus
Jisoo Lee and Sae-Young Chung
in International Conference on Learning Representations (ICLR), Addis Ababa, Ethiopia, Apr. 2020.
[Paper] [Slides] [OpenReview]
* this is an extended version of my MS thesis.
Teaching

2017.3 ~ 2017.6 : Undergraduate Teaching Assistant, CS101 Introduction to Programming, KAIST
2018.9 ~ 2018.12 : Teaching Assistant, EE807 Deep Reinforcement Learning and AlphaGo, KAIST (won the outstanding TA award)
2019.3 ~ 2019.6 : Teaching Assistant, EE485 Philosophical issues in AI, KAIST
Like

Contact Info