I am a PhD student in the Department of Industrial Engineering & Management Sciences at Northwestern University. I am primarily interested in robust and reliable machine learning. In particular, my research interests include diverse faces of generalization in machine learning and interfaces between people and machine learning models.

Email: tjoo at u dot northwestern dot edu
Google Scholar | GitHub | LinkedIn

Research

Revisiting explicit regularization in neural networks for well-calibrated predictive uncertainty.
Taejong Joo, Uijung Chung
arXiv, 2021
paper

Being Bayesian about categorical probability.
Taejong Joo, Uijung Chung, Min-Gwan Seo
International Conference on Machine Learning (ICML), 2020
paper | code

Regularizing activations in neural networks via distribution matching with the Wasserstein metric.
Taejong Joo, Donggu Kang, Byunghoon Kim
International Conference on Learning Representations (ICLR), 2020
paper

Formalizing human–machine interactions for adaptive automation in smart manufacturing
Taejong Joo, Dongmin Shin
IEEE Transactions on Human-Machine Systems, 2019
paper

An adaptive approach for determining batch sizes using the hidden Markov model
Taejong Joo, Minji Seo, Dongmin Shin
Journal of Intelligent Manufacturing, 2019
paper

Awards

Benjamin K. Sachs Graduate Fellowship (awarded to an exceptional incoming PhD student of the Department of Industrial Engineering & Management Sciences at Northwestern University)

Activities

Reviewer: ICML’21, NeurIPS’21, ICLR’22