Summary
Shihao Zhang is a PhD researcher at the National University of Singapore with eight years of experience bridging theoretical machine learning and practical medical imaging. His work focuses on deep regression representation learning—leveraging information theory and topology—to improve tasks like depth estimation, super-resolution, and pose/age estimation, with papers at ICML and ICLR and public codebases (PH-Reg, OrdinalEntropy). Earlier work applied advanced segmentation models to ophthalmology, producing a cataract grading index and multiple MICCAI publications and a best-paper award. Based in Singapore, he combines rigorous mathematical training (BSc Math, MSc Software Engineering) with hands-on translational research at clinical and industry labs, making theoretical insights applicable to real-world biomedical problems. An interesting thread across his work is reframing regression problems with tools usually reserved for classification or topology, yielding concrete gains in both understanding and performance.
8 years of coding experience
1 year of employment as a software developer
Master's degree, Software Engineering, Master's degree, Software Engineering at 华南理工大学
Doctor of Philosophy - PhD, School of Computing, Doctor of Philosophy - PhD, School of Computing at 新加坡国立大学