Research
Our research focuses on developing innovative AI models that are grounded in scientific insight and driven by real-world data. We investigate two complementary themes: using AI to gain deeper insights into the brain, and drawing inspiration from brain organization to advance AI.
Learning the Brain
Understanding the brain’s intricate network organization is key to revealing how it supports diverse functions and varies across individuals. We develop AI-driven methods to analyze the structure and dynamics of human brain networks. Our aim is to map and model these networks to uncover how structural connections give rise to functional activity and individual differences, contributing to the broader goals of connectomics.
Learning from the Brain
We translate insights from brain network organization into brain-inspired AI methodologies. By incorporating topological principles observed in brain connectivity into neural architectures, we aim to improve how AI systems learn, adapt, and generalize. Our research focuses on enabling models to retain knowledge over time, transfer learning across tasks, and integrate diverse sources of information, contributing to AI that is more flexible, robust, and interpretable.
If you are interested in these new learning paradigms, feel free to send me an email to discuss possible collaboration. Duke students who seek research experience, please reach out to me for research opportunities. To learn more about current open positions and how to apply, please visit the opportunities page. Email inquiries are welcome!