My PhD research can be summarized by the title of my thesis —
Exploring Complexity Reduction in Deep Learning. I developed a technique known as pre-defined sparsity to reduce the complexity of neural networks with minimal performance degradation. My latest project was on developing an open-source automated machine learning (AutoML) framework called Deep-n-Cheap to search for deep learning models and explore tradeoffs between performance and complexity. I also received an award for developing a family of open-source synthetic machine learning datasets.
My initial PhD research was on non-uniform sampling and mixed signal circuits. I then switched track and was involved in the inception and subsequent growth of a new machine learning group at USC in 2016. Some of my early work involved a hardware architecture, however, I have now completely moved over to the software and theoretical side. My current and future research interests include applying automated deep learning, interpretability of machine learning systems, data science and software engineering.
I like reading, particularly detective thrillers, science fiction and fantasy, and sports-related books. Here's my Goodreads profile, I'd love to connect with other bibliophiles! I am also a big fan of watching football. My ideal weekend is waking up in time to watch Chelsea play and (hopefully) win. Some other activities which I enjoy are swimming, programming, and blogging. Click on the image to read an article I wrote for the USC ECE department blog.