The University of Texas at San Antonio is using a $4 million grant from the National Science Foundation (NSF) to fund “The Neuromorphic Commons (THOR)” project, which will offer researchers access to a large-scale neuromorphic computing system.
The THOR project, which will be managed by the university’s MATRIX AI Consortium, will include research from the University of Texas at San Antonio, the University of Tennessee Knoxville, the University of California San Diego, and Harvard University.
“We plan to design a national hub for open access large scale neuromorphic platforms, through close-knit industry partnerships,” said Dhireesha Kudithipudi, principal investigator at the University of Texas at San Antonio. “The field is at a pivotal moment and ensuring access to a broader group of researchers is critical at this stage. This initiative reflects a community-driven approach, shaping a framework designed by and for the community.”
Taking inspiration from how the human brain works, the THOR project will work to facilitate a transformation in algorithm design, hardware and software co-design, and neuromorphic applications. The university explained that the impact of the THOR project will be similar in scale to the impact seen when high-performance computing systems first became accessible to the engineering research community. Additionally, THOR will be accessible to a diverse array of research communities, including computational neuroscience, life sciences, artificial intelligence, machine learning, and physics.
“This award is crucial in advancing NSF’s mission to drive innovation and broadening access to research resources,” said NSF Program Director Andrey Kanaev. “By making bio-inspired computing resources available to a wider community of researchers in computer science, neuroscience, and computational physics, this project will contribute to democratizing access to advanced tools and fostering breakthroughs in energy-efficient, resilient AI through neuromorphic computing.”
The THOR team will also develop training and educational materials covering the fundamentals of neuromorphic learning algorithms and systems. All resources will be available through open platforms to researchers, facilitating integration into both undergraduate and graduate curricula.
