Federal Grant Award Summary

Montclair State University received a $199,494 Engineering Research Initiation (ERI) grant from the National Science Foundation's Division of Electrical, Communications and Cyber Systems (CFDA 47.041) awarded June 1, 2026, with completion by May 31, 2028. The project delivers research and development of back propagation-free split learning methods designed to enable collaborative machine learning across distributed edge systems with heterogeneous computing and networking capabilities. Key deliverables include theoretical foundations and algorithmic designs for split neural networks that replace computationally expensive gradient exchanges with lightweight scalar updates, reducing communication overhead for resource-constrained devices such as wearables and mobile platforms while maintaining model training capability without raw data sharing between devices and servers.

The award also encompasses educational and workforce development outcomes through research-integrated training activities, as well as the release of open-source tools and benchmarks to support the broader research and education communities. These products are specifically designed to expand access to advanced machine learning capabilities for organizations and communities with limited computing and networking resources, addressing practical implementation challenges in real-world edge computing environments where devices operate under heterogeneous conditions.