Linhai Ma

I obtained my Ph.D. from the Department of Computer Science at the University of Miami, under the supervision of Dr. Liang Liang. During my Ph.D. period, my research focused on improving the robustness of deep neural networks against adversarial noises. I proposed variant methods to achieve this goal, including regularization and adversarial training. Besides conducting experiments on basic classification tasks of natural images, I proposed methods to improve the robustness of models for more complicated tasks in medical imaging domains, e.g., ECG signal automatic diagnosis, MRI image segmentation, Cephalometric landmark detection, and blood cell detection.

I got my master’s degree from the State Key Laboratory of Computer Science (SKLCS), Institute of Software, Chinese Academy of Sciences (ISCAS), working with Dr. Peng Wu. During my pursuit of a master’s degree, my primary research focus was in the area of software testing and concurrency. I proposed an adaptive algorithm to test C++ concurrent data structures based on the coverage criterion.