Yixiu Zhao

Stanford Interdisciplinary Graduate Fellow (Anonymous Donor)
PhD Student
Applied Physics
Affiliation:
Interdisciplinary Graduate Fellows in Neuroscience

Born in Nanjing, China, Yixiu Zhao is a PhD student in the Applied Physics department working in the Linderman Lab on computational neuroscience and machine learning with Dr. Scott Linderman. Yixiu has a wide variety of research interests, including building structured models for statistical inference, making neuroscientific inquiries with machine learning, and better understanding the high-level principles of human and artificial intelligence. His current project involves combining Bayesian inference and deep neural networks for behavioral studies of mice. Before coming to Stanford, Yixiu earned his B.S. degree in Computer Science from the School of Computer Science at Carnegie Mellon University, with a second major in Math and a minor in Physics.

Apart from research, Yixiu also dabbles in singing, cooking, and designing weird video games that he never gets to finish. Sometimes he wonders if an academic paper or a video game will be the first publication in his PhD. In his opinion, either would be fine.

Related Projects

Wu Tsai Neurosciences Institute
SIGF - Graduate Fellowship
2021
Inference via Abstraction: A framework for efficient Bayesian cognition

We propose a novel framework for efficient Bayesian cognition called Inference via Abstraction (IvA), which learns to approximate complex world models with simpler abstractions that capture main dependencies, but leverage structure in the prior distribution for efficient inference. We instantiate IvA with a combination of probabilistic graphical models and deep neural networks.