跳到主要内容
news

著名学者黄任祥教授重新定义主成分分析在数据分析中的解释

返回

Photo 1

 

Professor Limsoon Wong, a prominent scholar in the field of knowledge discovery technologies and biomedicine from the National University of Singapore (NUS), delivered an enlightening lecture titled “The Hidden Truths of Principal Component Analysis” on October 18,2024.

 

In his sharing, Professor Wong redefined the conventional view of Principal Component Analysis (PCA), shed light on its often-overlooked capabilities beyond its common uses for dimension reduction and data visualisation. While it is typically assumed that most significant variations in PCA are found in the first few principal components, he demonstrated that even principal components accounting for less than 1% of the total variance can yield valuable insights. Furthermore, he highlighted that PCA deconvolutes data variations into meaningful directions and underscored the importance of discerning noise within the data, as the leading principal components may sometimes reflect irrelevant or confounding information. Professor Wong's insights not only clarified the intricate workings of PCA but also paved the way for a more nuanced and effective application in data analysis.

 

Professor Limsoon Wong, Kwan-Im-Thong-Hood-Cho-Temple Professor in Computing at the NUS, currently works mostly on knowledge discovery technologies and their application to biomedicine. He has also done significant research in database query language theory and finite model theory, as well as significant development work in broad-scale data integration systems. Recognised for his contributions to database theory and computational biology, he was inducted as a Fellow of the ACM in 2013 and as a Fellow of the Singapore National Academy of Science in 2024.

 

View the video here.

View more photos here.