吳沛遠助理教授的個人資料 - Profile of Pei-Yuan Wu

吳沛遠 Pei-Yuan Wu

國立台灣大學電機工程學系 助理教授
Assistant Professor, Department of Electrical Engineering, National Taiwan University

主要研究領域:

機器學習,主動辨識,估計理論,智慧製造

Major Research Areas:

machine learning, active authentication, estimation theory, smart manufacturing

研究領域摘要:

1. 主動識別: 本研究團隊與普林斯頓大學及愛荷華州立大學合作,透過分析人機互動過程中使用者的生物特徵與行為特徵進行持續性且非干擾性身分識別。(CBS news: https://www.cnet.com/news/one-way-to-make-passwords-obsolete-just-keep-typing/)

2. 隱私維護機器學習: 將同態加密、亂碼電路等加密機制加入機器學習演算法,以降低個人隱私資料在機器學習中遭到揭露的風險。

3. 核方法: 提升核方法的運算效率與強健性,以應用於大數據分析。

4. 深度學習應用: 場景文字識別、影像除霧、姿態識別。

Research Summary:

1. Privacy Preserving Machine Learning:  We study the embedding of cryptography, such as homeomorphic encryption and garbled circuits, into machine learning algorithms, in order to reduce the risk of exposing confidential personal information.

2. Active Authentication: In collaboration with Princeton University and Iowa State University, we study how to continuously and unintrusively authenticate user's identity based on his/her behavior biometrics. (CBS news: https://www.cnet.com/news/one-way-to-make-passwords-obsolete-just-keep-typing/)

3. Kernel Methods: We study the cost-effectiveness and robustness issues in kernel-based machine learning.

4. Deep Learning Applications: Scene text recognition, image dehazing, pose estimation. 

Photo of Pei-Yuan Wu