Xiaomin Li

I am a Ph.D. student at Texas State University majoring in Computer Science. I have a strong research background with expertise in using Machine Learning and Deep Learning methods to analyze time-series data and image data.

My dissertation topic is to solve the bio-signals data shortage problem when training them on very deep Deep Learning models. I have used supervised, unsupervised, and self-supervised machine learning algorithms as well as transfer learning to reuse general signal features learned from large datasets on small target datasets. I have also used Generative Adversarial Networks (GANs) to generate high fidelity synthetic data that can be used as data augmentation tools to enlarge the training datasets.

Other than that, I also have a deep understanding in the fields of deep learning model compressions, deep learning on edge devices, efficient object detections, autonomous driving, and computer graphics.