M
Minseop Park
Researcher at Sungkyunkwan University
Publications - 9
Citations - 788
Minseop Park is an academic researcher from Sungkyunkwan University. The author has contributed to research in topics: Test set & Task (project management). The author has an hindex of 7, co-authored 8 publications receiving 537 citations.
Papers
More filters
Proceedings Article
Learning to propagate labels: Transductive propagation network for few-shot learning
TL;DR: This paper proposes Transductive Propagation Network (TPN), a novel meta-learning framework for transductive inference that classifies the entire test set at once to alleviate the low-data problem.
Posted Content
Transductive Propagation Network for Few-shot Learning
TL;DR: This paper proposes Transductive Propagation Network (TPN), a transductive method that classifies the entire test set at once to alleviate the low-data problem and explicitly learns an underlying manifold space that is appropriate to propagate labels from few-shot examples.
Journal ArticleDOI
A deep learning model for real-time mortality prediction in critically ill children
Soo Yeon Kim,Saehoon Kim,Joongbum Cho,Young Suh Kim,In Suk Sol,Youngchul Sung,Inhyeok Cho,Minseop Park,Haerin Jang,Yoon Hee Kim,Kyung Won Kim,Myung Hyun Sohn +11 more
TL;DR: A deep model-based, data-driven early warning score tool that can predict mortality in critically ill children and may be useful for the timely identification of deteriorating patients is developed and validated.
Proceedings Article
Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning
TL;DR: Transductive Propagation Network (TPN) as discussed by the authors proposes to propagate labels from labeled instances to unlabeled test instances by learning a graph construction module that exploits the manifold structure in the data.
Proceedings Article
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks
TL;DR: In this article, the authors propose a novel meta-learning model that adaptively balances the effect of the meta learning and task-specific learning within each task, and formulate this objective into a Bayesian inference framework and tackle it using variational inference.