eprintid: 3725
rev_number: 9
eprint_status: archive
userid: 4
dir: disk0/00/00/37/25
datestamp: 2019-12-06 08:24:28
lastmod: 2019-12-06 08:24:28
status_changed: 2019-12-06 08:24:28
type: conference_item
metadata_visibility: show
creators_name: Nguyen, Duy Anh
creators_name: Bui, Duy Hieu
creators_name: Iacopi, Francesca
creators_name: Tran, Xuan Tu
creators_id: danguyen@vnu.edu.vn
creators_id: hieubd@vnu.edu.vn
creators_id: Francesca.Iacopi@uts.edu.au
creators_id: tutx@vnu.edu.vn
title: An Efficient Event-driven Neuromorphic Architecture for Deep Spiking Neural Networks
ispublished: pub
subjects: ECE
subjects: ElectronicsandComputerEngineering
divisions: fac_fet
divisions: lab_sis
abstract: Deep Neural Networks (DNNs) have been successfully
applied to various real-world machine learning applications.
However, performing large DNN inference tasks in real-time
remains a challenge due to its substantial computational costs. Recently, Spiking Neural Networks (SNNs) have emerged as an alternative way of processing DNN’s task. Due to its eventbased, data-driven computation, SNN reduces both inference latency and complexity. With efficient conversion methods from traditional DNN, SNN exhibits similar accuracy, while leveraging many state-of-the-art network models and training methods. In this work, an efficient neuromorphic hardware architecture for image recognition task is presented. To preserve accuracy, the analog-to-spiking conversion algorithm is adopted. The system aims to minimize hardware area cost and power consumption, enabling neuromorphic hardware processing in edge devices. Simulation results have shown that, with the MNIST digit recognition task, the system has achieved ×20 reduction in terms
of core area cost compared to the state-of-the-art works, with an accuracy of 94.4%, core area of 15 μm2 at a maximum frequency of 250 MHz.
date: 2019-09-03
date_type: published
contact_email: tutx@vnu.edu.vn
full_text_status: restricted
pres_type: paper
event_title: 2019 32nd IEEE International System-on-Chip Conference (SOCC)
event_location: Singapore
event_dates: 3-6 September 2019
event_type: conference
refereed: TRUE
citation:   Nguyen, Duy Anh and Bui, Duy Hieu and Iacopi, Francesca and Tran, Xuan Tu  (2019) An Efficient Event-driven Neuromorphic Architecture for Deep Spiking Neural Networks.  In: 2019 32nd IEEE International System-on-Chip Conference (SOCC), 3-6 September 2019, Singapore.     
document_url: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/3725/1/PID6057229.pdf