The U.S. National Science Foundation (NSF) awarded a $120,120 CAREER grant under the Computer and Information Science and Engineering (CISE) program to The Johns Hopkins University. The project, titled "DEEPMATTER: A Scalable and Programmable Embedded Deep Neural Network", will develop novel methodologies for optimizing deep neural network (DNN) models to enable their deployment on embedded systems with limited hardware resources and power budgets. The research aims to create new DNN architectures, a programmable domain-specific hardware platform, and an application program interface (API) to allow rapid prototyping and deployment of intelligent applications on embedded devices. The effort will demonstrate the technology through five applications including multi-physiological processing, multi-modal assistance, air quality monitoring, and vision-based situational awareness. The project period is from October 1, 2023 to April 30, 2024, and no sub-awards are planned.
Generated 8/13/24, 3:33 AM