Dr. Tianyun Zhang, an assistant professor in the Department of Electrical Engineering and Computer Science (EECS), has been awarded a two year, $174,233 grant from the National Science Foundation (NSF) for research on Edge Computing. Edge Computing involves distributed computing with localized calculations and decision making, as opposed to centralizing data storage and computation in the cloud. Cloud-based computing can result in a lag while data is uploaded, processed, and then communicated back.

The project, titled "A Systematic Multi-Task Learning Framework for Improving Deep Learning Efficiency on Edge Platforms," is funded by the NSF's Division of Computer and Network Systems (CNS). Multi-task learning is a subfield of machine learning in which a shared model is used to solve different tasks simultaneously. For example, there are multiple tasks to be done in real-time in self-driving cars, including object detection and depth estimation. If these tasks can be trained on a single model with shared parameters, the model size and the inference time can be significantly reduced. Dr. Zhang's project proposes an approach to learn the difficulty of every task and maintain the performance of the most difficult task when compressing a multi-task learning model.

The research will include both undergraduate and graduate students, and will generate research demonstrations that will engage K-12 students and help promote the pursuit of STEM-related careers. Additionally, the research will be incorporated into a current senior-level undergraduate course, a future advanced-level graduate course and seminars for undergraduate and graduate students.