I am a Computer Science PhD student at Harvard advised by Hanspeter Pfister, and collaborating closely with Xavier Boix, Gabriel Kreiman and Tomaso Poggio at CBMM. My research focusses on understanding the generalization capabilities of machine learning models. 

Generalizing beyond training data is the fundamental goal of machine learning. While standardized datasests have lead to unprecedented success in computer vision, understanding how these models generalize beyond them is essential for building robust, trustable models which can be deployed in the society with confidence. To this end, I study generalization behavior of neural networks using fine-grained, controlled datasets created using Computer Graphics (CG).