Convolutional Neural Networks on Embedded Reconfigurable Architectures
Overview
Currently, the convolutional neural network (CNN) is one of the most used deep learning models for image detection and classification. CNNs achieve better results at the cost of higher computing and memory requirements. CNN is therefore usually done in centralized high-performance platforms. However, many applications based on CNNs are migrating to edge devices near the source of data. Deep learning on edge is quite challenging because edge devices are usually limited in terms of performance, cost, and energy. Reconfigurable computing is being considered for inference on edge due to its high performance and energy efficiency while keeping a high hardware flexibility that allows for the easy adaption of the target computing platform to the CNN model.
In this project, we aim to develop hardware-software co-design solutions for CNNs on embedded reconfigurable computing architectures like FPGAs - in combination with other embedded devices - for achieving an efficient computing platform on the edge devices for AI and IoT applications.
Duration
24 months (08/2019 - 08/2021)
Project code
This research is funded by Funds for Science and Technology Development of the University of Danang under project number B2019-DN02-61.
Nghiên cứu này được tài trợ bởi Quỹ Phát triển khoa học và công nghệ Đại học Đà Nẵng trong đề tài có mã số B2019-DN02-61.
Members
Dr. Huynh Viet Thang, Principal Investigator
Dr. Ho Phuoc Tien, Member
Dr. Phan Tran Dang Khoa, Member
MEng. Vu Van Thanh, Secretary