CIRC: Grand: The Neuromorphic Commons (THOR)

University Of Texas At San Antonio, San Antonio TX

Investigators

Abstract

The neuromorphic commons (THOR) project aims to accelerate the pace of research innovation by creating a new and unparalleled large-scale neuromorphic computing resource, providing unique opportunities for cooperation in research collaborations and tool development. By lowering the barriers to access neuromorphic infrastructure through collaborations with two prominent neuromorphic companies, and by providing open-source software frameworks and benchmarks, THOR will drive research advancements in multiple application domains. THOR will catalyze a transformation in algorithm design, hardware/software co-design paradigms, and neuromorphic applications, similar in scale to the impact seen when high-performance computing systems became accessible to the engineering research community. The THOR project involves researchers from the University of Texas at San Antonio, the University of Tennessee Knoxville, the University of California San Diego, and Harvard University. The project aims to develop and deploy large-scale neuromorphic computing research infrastructure which will provide community access to heterogeneous neuromorphic computing hardware systems through close-knit partnership with industry. THOR offers i) remote access to large-scale neuromorphic systems; ii) open-source hardware/software co-design frameworks and tools; iii) common benchmarks and competitions; and iv) rapid algorithm development by providing access to a collection of learning modules, network models, and example frameworks. THOR will enable a richer understanding of computational models, algorithms, neuromorphic hardware, and engineered test cases, supporting research in neuroscience and a wide range of application domains that benefit from bioinspired processing. THOR team will develop training and educational materials that will cover the fundamentals of neuromorphic learning algorithms and systems, in partnership with industry and the neuromorphic community. All the resources will be available through open-platforms to researchers and K-12 students, facilitating integration into both undergraduate and graduate curricula. 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.