Collaborative Research: EAGER: Human Brain Modeling via Quantum Machine Intelligence

Understanding the human brain is a vital area of research with broad scientific and societal importance. Revealing the underlying mechanisms of brain function has the potential to advance medical diagnosis and treatment planning for neurological and psychiatric disorders, e.g., Parkinson's disease, obsessive-compulsive disorder, and many others. In addition, a deeper understanding of brain processes and how the brain represents information can inspire the development of the next generation of Artificial Intelligence (AI) systems and significantly benefit a wide range of scientific and engineering fields. At the same time, quantum computing offers new ways to represent and process complex information, but its potential for understanding the human brain remains largely unexplored. This project aims to develop new quantum machine intelligence approaches for modeling human brain activity using functional magnetic resonance imaging data. The outcomes of this project could advance scientific understanding of neuroscience and quantum machine learning and inspire more efficient AI systems. The project will also support student training, interdisciplinary education, public workshops, webinars, open-source software, and collaborations that broaden access to research at the intersection of quantum computing, neuroscience, and artificial intelligence. Despite the urgent need to accurately model human brain activity, research on quantum machine intelligence has been limited, particularly for analyzing large-scale functional magnetic resonance imaging data to advance vision-brain understanding. Existing machine learning approaches often struggle to represent complex, high-dimensional, and brain-wide neural dynamics, while current quantum machine learning methods remain underdeveloped for human brain understanding. To address these limitations, this project will develop a new framework for vision-brain understanding by integrating quantum theory with machine learning models for functional magnetic resonance imaging. First, the project will introduce new quantum-inspired neural networks that leverage superposition and entanglement to model complex relationships between visual stimuli and brain activity. Second, a new quantum feature encoding will be developed to represent large-scale brain imaging signals in a quantum feature space, improving the ability to capture high-dimensional neural patterns with higher fidelity and better task performance. Third, the project will propose a novel hierarchical quantum circuit gate model that operates on quantum machines for scalable vision-brain modeling. All algorithms developed will be released as open-source software to support accessibility and reproducibility. This project is expected to advance human brain understanding, quantum machine learning, and brain-inspired vision systems by enabling richer, more scalable modeling of complex brain-wide dynamics. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria. NSF Award ID: 2602772 | Program: 01002627DB NSF RESEARCH & RELATED ACTIVIT | Principal Investigator: Khoa Luu | Institution: University of Arkansas, FAYETTEVILLE, AR | Award Amount: $149,960 View on NSF Award Search: https://www.nsf.gov/awardsearch/show-award/?AWD_ID=2602772 View on Research.gov: https://www.research.gov/awardapi-service/v1/awards/2602772.html