ECE Professor Yingying Chen is a recipient of a new National Science Foundation (NSF) award for the project titled "Software Hardware Architecture Co-design for Low-power Heterogeneous Edge Devices" This is a three-year project of $500,000 in collaboration with Binghamton University. The Rutgers share of the award is $320,000.
In this project, Yingying and her team aim to remove the barrier that keeps deep learning techniques away from pervasive low-power mobile edge computing devices and enable high-accuracy, low-latency applications in future mobile edge computing. This research plans to systematically investigate the fundamental and challenging issues targeting to significantly reduce the cost of deep learning inference process in mobile edge devices with guaranteed performance. The team will build a software accelerator that enables the broad deployment of heavy-cost deep learning models into resource-constrained, heterogeneous mobile edge devices (e.g., low-cost sensing platforms and IoT devices). They will develop deep-learning resource management algorithms that can adjust structures of different deep learning models according to hardware constraints of heterogeneous edge devices. More specifically, this research analyzes distinct deep learning behaviors on mobile edge devices and designs different strategies to improve the efficiency of multiple deep-learning-based inference models. Furthermore, this research develops algorithms that can adjust the complexity of different deep learning models to reduce their energy and memory consumption on mobile edge devices. In addition, this project designs power-centric resource reallocation algorithms to verify and deploy the mobile-friendly deep learning models.
You can find more details on the project at the NSF page here: