Bo Yuan receives NSF Grant for Advancing On-Device Inference and Learning in Deep Neural Networks

ECE Assistant Professor Bo Yuan is the recipient of a new NSF award for the research project titled "TensorNN: An Algorithm and Hardware Co-design Framework for On-device Deep Neural Network Learning using Low-rank Tensors." Dr. Yuan is the lead PI on a three-year $1.2 million collaborative effort between Rutgers, Columbia University and University of Minnesota.

In this project, Dr. Yuan and his team aim to advance efficient on-device inference and learning for deep neural networks (DNNs). In order to achieve stronger data privacy, less response time and relaxed data transmission burden, deploying DNN functionality in a distributed manner at the edges of the network has become a very attractive proposition. However, DNN-learning on mobile devices that are at the edge of the network is very challenging due to conflicting requirements of large time and energy consumption, and limited on-device resources. In order to address this challenge, this project leverages low-rank tensors as a powerful mathematical tool for representing and compressing tensor-format data, to form a new family of ultra-low cost deep neural networks. This brings an order-of-magnitude reduction in time and energy consumption for deep neural network learning. Investigations in many areas of BigData research will benefit as well. This project involves graduate and undergraduate students, especially from underrepresented groups, through summer research experiences, and senior design projects to broaden the participation of computing. The outcomes of this project will be disseminated to the community in the format of technical publications, talks and tutorials in both academic institutions and industry.

You can find more details on the project at the NSF page

Congratulations Bo!