I am a researcher at the Thousand Brains Project , where I study how intelligent agents learn representations of objects through movement and sensation. My current work focuses on sensorimotor learning, object recognition, and computational principles inspired by the neocortex.
More broadly, I am interested in how biological and artificial systems construct useful representations of the world. What information should a system preserve? How should it represent structure, movement, uncertainty, and equivalence? And how do these representations support robust learning and inference?
My path to these questions began in biology. As an undergraduate in bioengineering at UC Berkeley, I focused on microfluidics and technologies for studying individual cells. During my Ph.D. in Electrical Engineering and Computer Science at the University of Michigan, I developed generative models connecting single-cell gene expression and neuronal morphology.
Across these areas, I have been most drawn to research problems that require learning a new field, developing an appropriate computational representation, and testing it in a working system. My work has gradually moved from modeling individual cells and neurons toward understanding the computational principles that allow intelligent agents to learn about and interact with their environments.
Current work
At the Thousand Brains Project, I contribute to Monty, an open-source framework for sensorimotor intelligence. My work includes developing sensory representations and investigating how objects, poses, and symmetries can be represented for robust learning and recognition.
Education
University of Michigan, Ann Arbor
Ph.D. and M.S. in Electrical Engineering and Computer Science
University of California, Berkeley
B.S. in Bioengineering
Outside research
Outside of research, I enjoy reading, exploring bookstores and libraries, and spending time with my golden retriever, Arthur. 🐾