Investigator: Jungpil Hahn, Ke-Wei Huang. In today’s big data environment, missing values continue to be a problem that harms data quality. The bias caused by missing values raises the highest concern, …
Investigator: Lee Wee Sun. Most AI problems are computationally intractable in the worst case. The typical or average case could be much easier but is difficult to design for. We propose to use machine learning …
Investigator: Jonathan Scarlett. Black-box function optimization via expensive noisy samples have diverse applications in problems such as hyperparameter tuning, robotics, and molecular design. Various algorithms have previously been proposed with rigorous …
Investigator: Vaibhav Rajan. The increasing availability of digitized clinical data presents an unprecedented opportunity to study and gain deeper understanding of diseases, develop new treatments and improve healthcare ecosystems, and to …
Investigator: Angela Yao. Assembly101 is a new procedural activity dataset featuring 4321 videos of people assembling and disassembling 101 “take-apart” toy vehicles. Participants work without fixed instructions, and the sequences feature …
Investigators: Wynne Hsu and Lee Mong Li. A deep learning-based screening system that examines retinal fundus photographs for various eye conditions, including diabetic retinopathy, age-related macular degeneration (AMD) and glaucoma. …