Yen-Cheng Chang (Timothy)
Ph.D. student,
Signal Processing & Machine Learning,
Electrical and Computer Engineering,
University of Michigan-Ann Arbor
I am currently a PhD student in the Department of Electrical and Computer Engineering at the University of Michigan, working with Pei Zhang. Previously, I was a machine learning researcher at E.SUN Financial Holding, where I conducted research with Professor Yi-Ren Yeh and Professor Jyh-Shing Roger Jang. I received my M.S. degree in Electrical Engineering and Computer Sciences at National Taiwan University (NTU) under the guidance of Professor Tian-Li Yu. Prior to NTU, I received B.S. in Computer Science and Information Engineering from National Taipei University (NTPU).
My primary research focuses on domain adaptation, active learning, and synthetic data generating, eliminating the need for manual labels on signal and image processing. For further studies, I am excited about explicitly modeling structure in data for system analysis. At the same time, I am also interested in topics related to potential applications in machine learning systems.
I have research experience in image & signal processing and machine learning for about three years and published three international conference papers: ICIP 2022 (as the first author), INTERSPEECH 2022, and ICPR workshop 2022 . In addition, I got the NTU EE Best Thesis Award 2020.
My primary research focuses on domain adaptation, active learning, and synthetic data generating, eliminating the need for manual labels on signal and image processing. For further studies, I am excited about explicitly modeling structure in data for system analysis. At the same time, I am also interested in topics related to potential applications in machine learning systems.
I have research experience in image & signal processing and machine learning for about three years and published three international conference papers: ICIP 2022 (as the first author), INTERSPEECH 2022, and ICPR workshop 2022 . In addition, I got the NTU EE Best Thesis Award 2020.
Publications
• SMILE: Sequence-to-Sequence Domain Adaption with Minimizing Latent Entropy for Text Image Recognition. Yen-Cheng Chang, Yi-Chang Chen, Yu-Chuan Chang, and Yi-Ren Yeh, ICIP, 2022. [pdf]• g2pW: A Conditional Weighted Softmax BERT for Polyphone Disambiguation in Mandarin. Yi-Chang Chen, Yu-Chuan Chang, Yen-Cheng Chang, and Yi-Ren Yeh, INTERSPEECH, 2022. [pdf]
• Traditional Chinese Text Recognition Dataset: Synthetic Dataset and Labeled Data. Yi-Chang Chen, Yu- Chuan Chang, Yen-Cheng Chang, and Yi-Ren Yeh, ICPR Workshop, 2022. [pdf]
• Verifiability Enhanced Active Learning Using Multi-armed Bandit. Yen-Cheng Chang and Tian-Li Yu, Master's Thesis, Computer Science Group, Department of Electrical Engineering, National Taiwan University. [pdf]
Works & Honors
• T-Brain AI Competition: AICUP2021 Traditional Chinese scene text recognition, 2nd Place, 2021• Best Master’s Thesis award, National Taiwan University, Department of EECS, 2020
• Developer in Cinnamon.ai AI Document Reader, Cinnamon AI, 2019
• Zhen lin Science Education Center Advanced High School Mathematics Class, Teaching Assistant, 2019