I am currently a Ph.D. student in the Electrical & Computer Engineering at Rice University and the Neuroscience Department at Baylor College of Medicine (BCM), where I work in the DSP group with Dr. Richard Baraniuk and in the Deep Learning group with Dr. Ankit Patel. My research is focused on the intersection of Deep Learning, Probabilistic Modeling, and Neuroscience. In particular, I develop neuro-inspired Deep Learning algorithms from proper generative probabilistic models such as the Deep Rendering Mixture Models. I received my BSEE from Rice in May 2014. While being an undergraduate at Rice, I was a part of the DSP group, where I conducted research in signal processing and computational neuroscience. I also worked in Dr. Robert Hauge‘s research group, where I investigated the effect of temperature and pressure on the collapse of carbon nanotubes. In the summer of 2012 and 2011, I was an undergraduate research assistant in Dr. Zhu Han‘s lab at the University of Houston and Dr. Stephan Link‘s lab at Rice University, respectively.
I want to understand the generative probabilistic models underlying deep learning systems, including the Deep Convolutional Networks (DCNs) and the Random Decision Forests. Using these models and inspired by the brain’s structures, I develop new deep learning algorithms for solving practical problems. In particular, my advisors and I invented the Deep Rendering Mixture Model, the first graphical models whose inference is exactly a DCN. The DRMM unifies two perspectives: neural network and probabilistic inference. Using the DRMM, I developed a new semi-supervised learning algorithm that achieves state-of-the-art performance on multiple benchmarks, including MNIST, SVHN and CIFAR10.