In my current research, I explore the utility of machine learning algorithms and artificial intelligence, especially deep convolutional neural networks, in quantum computing platforms. At present, I am investigating methods to automatically identify stable configurations of electron spins in semiconductor-based quantum systems. I am also developing a complete software suite that enables modeling of quantum dot devices, train recognition networks, and — through mathematical optimization — auto-tune experimental setups. Success in this endeavor will eliminate the need for heuristic calibration and help scale up quantum computing into larger quantum dot arrays.
In education research, I am specifically interested in understanding what factors affect student retention and persistence in pursuing their degree. Using social network analysis, I look at the correlations between students’ overall embeddedness within the in- and out-of-class network and their odds of persistence into the second semester in a sequence. I also investigate how the attitudes toward learning with peers translate into actual behaviors. My objective is to provide a concrete basis for efforts to increase overall student retention and graduation rates at both the departmental and university levels. As part of this project, I am also developing a suite (in the R programming language) for manipulation, visualization and statistical analyses of network data.