This Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program, CFDA 47.070, provides $900,000 to the University of California, Irvine to develop a neurosymbolic framework called NEUHLS for high-level synthesis of multi-task learning models. The goal is to enable high-performance deep neural network models to be efficiently deployed on edge devices with strict latency and hardware constraints, such as in virtual/augmented reality and assistive robotics applications. The NEUHLS toolchain integrates multi-task learning, neurosymbolic AI, and high-level synthesis techniques to merge, compress, and synthesize deep neural networks while optimizing for accuracy, hardware utilization, and latency. The project aims to positively impact the adoption of smart and autonomous systems by enabling their deployment on resource-constrained hardware. The award period is from October 1, 2025 to September 30, 2029.
Mod # | Description | Reason For Modification | Federal Obligation (Click to sort descending) | Date (Click to sort ascending) |
|---|---|---|---|---|
| Not listed | $900.0k | 7/8/25 |