I'm an AI Resident on the Google Brain team. I'm particularly interested in how we can develop more robust and interpretable machine learning models that we can trust in important, people-facing domains, like healthcare.
My current research is in developing computer vision models that are more stable and reliable. Computer vision models today achieve impressive results on benchmark tasks like Imagenet. However, they are still sensitive to small changes in the input image and can often exhibit low recall in real world applications. To that end, I'm interested in ways to leverage video data to learn more robust and general visual representations through unsupervised and semi-supervised approaches. I'm also interested in improving current methods for transfer learning and recent work on sparsity in deep learning.
Prior to the Residency, I was a Masters student in AI at Stanford, where I graduated with an undergraduate degree in Computer Systems in 2018. At Stanford, I did research on deep reinforcement learning and ways to combine model-based and model-free reinforcement learning techniques. I also worked on applications of deep learning to the healthcare domain, where I worked on problems in medical imaging and electronic health record data in collaboration with the medical school. Outside of work, I love reading, playing tennis, and cycling.