I'm a fourth year PhD student in Machine Learning at the Georgia Institute of Technology. I'm fortunate to be co-advised by Dr. Morris Cohen and Dr. Mark Davenport, and I'm happy to annouce that I am currently supported by the NDSEG Fellowship.
I graduated in May 2018 with my Bachelors in Electrical Engineering from the University of Kansas. I was exposed to applied statistics, optimization, and linear algebra early on during research positions in radar signal processing. I was also very lucky to do research internships at Systems & Technology Research (last time I checked, I was still on the front page!).
My research is focused on representation learning for the purposes of regression and anomaly detection in applications involving time series. One example is the application of LSTMs and Autoencoders to forecasting magnetic activity at Earth. Such activity is the result of processes occurring at the sun and could potentially have catastrophic effects on GPS and power networks at Earth. Images of the sun often contain information about these coronal processes, but such data must be embedded into a low-dimensional latent space to be of use to forecasting models. I am also interested in explainability in machine learning. In particular, i'm interested in drawing conclusions from ML results that motivate decision making by people who are otherwise unfamiliar with machine learning.