no code implementations • 28 Jul 2023 • Chan Hsu, Wei-Chun Huang, Jun-Ting Wu, Chih-Yuan Li, Yihuang Kang
In this study, we address the interpretability issue in complex, black-box Machine Learning models applied to sequence data.
no code implementations • 28 Jun 2021 • Yihuang Kang, Yi-Wen Chiu, Ming-Yen Lin, Fang-Yi Su, Sheng-Tai Huang
Machine Learning (ML) and its applications have been transforming our lives but it is also creating issues related to the development of fair, accountable, transparent, and ethical Artificial Intelligence.
no code implementations • 8 Oct 2020 • Sheng-Tai Huang, Yihuang Kang, Shao-Min Hung, Bowen Kuo, I-Ling Cheng
Researchers have been overwhelmed by the explosion of research articles published by various research communities.
no code implementations • 4 Jul 2020 • Bowen Kuo, Yihuang Kang, Pinghsung Wu, Sheng-Tai Huang, Yajie Huang
Patients with Acute Kidney Injury (AKI) increase mortality, morbidity, and long-term adverse events.
no code implementations • 3 Jul 2019 • Yihuang Kang, I-Ling Cheng, Wenjui Mao, Bowen Kuo, Pei-Ju Lee
In this paper, we discuss the machine learning interpretability of a real-world application, eXtreme Multi-label Learning (XML), which involves learning models from annotated data with many pre-defined labels.
no code implementations • 12 Jul 2018 • Yihuang Kang, Vladimir Zadorozhny
Our experimental result shows that the proposed approach can answer a kind of question-"what are the most frequent sequence of system dynamics relevant to a given sequence of observable events?".
no code implementations • 12 Jul 2018 • Yihuang Kang, Keng-Pei Lin, I-Ling Cheng
Due to recent explosion of text data, researchers have been overwhelmed by ever-increasing volume of articles produced by different research communities.
no code implementations • 9 Jul 2018 • Yihuang Kang, Vladimir Zadorozhny
In this paper, we consider monitoring temporal system state sequences to help detect the changes of dynamic systems, check the divergence of the system development, and evaluate the significance of the deviation.