Show simple item record

dc.contributor.authorGuo, Wenzhe
dc.contributor.authorYantir, Hasan Erdem
dc.contributor.authorFouda, Mohamed E.
dc.contributor.authorEltawil, Ahmed
dc.contributor.authorSalama, Khaled N.
dc.identifier.citationGuo, W., Yantır, H. E., Fouda, M. E., Eltawil, A. M., & Salama, K. N. (2020). Towards Efficient Neuromorphic Hardware: Unsupervised Adaptive Neuron Pruning. Electronics, 9(7), 1059. doi:10.3390/electronics9071059
dc.description.abstractTo solve real-time challenges, neuromorphic systems generally require deep and complex network structures. Thus, it is crucial to search for effective solutions that can reduce network complexity, improve energy efficiency, and maintain high accuracy. To this end, we propose unsupervised pruning strategies that are focused on pruning neurons while training in spiking neural networks (SNNs) by utilizing network dynamics. The importance of neurons is determined by the fact that neurons that fire more spikes contribute more to network performance. Based on these criteria, we demonstrate that pruning with an adaptive spike count threshold provides a simple and effective approach that can reduce network size significantly and maintain high classification accuracy. The online adaptive pruning shows potential for developing energy-efficient training techniques due to less memory access and less weight-update computation. Furthermore, a parallel digital implementation scheme is proposed to implement spiking neural networks (SNNs) on field programmable gate array (FPGA). Notably, our proposed pruning strategies preserve the dense format of weight matrices, so the implementation architecture remains the same after network compression. The adaptive pruning strategy enables 2.3× reduction in memory size and 2.8× improvement on energy efficiency when 400 neurons are pruned from an 800-neuron network, while the loss of classification accuracy is 1.69%. And the best choice of pruning percentage depends on the trade-off among accuracy, memory, and energy. Therefore, this work offers a promising solution for effective network compression and energy-efficient hardware implementation of neuromorphic systems in real-time applications.
dc.description.sponsorshipWe acknowledge the financial support from King Abdullah University of Science and Technology (KAUST), Saudi Arabia.
dc.publisherMDPI AG
dc.rightsThis article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.
dc.titleTowards Efficient Neuromorphic Hardware: Unsupervised Adaptive Neuron Pruning
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentElectrical Engineering
dc.contributor.departmentElectrical Engineering Program
dc.contributor.departmentSensors Lab
dc.eprint.versionPublisher's Version/PDF
dc.contributor.institutionDepartment of Electrical Engineering and Computer Science, University of California-Irvine, Irvine, CA 92612, USA.
kaust.personGuo, Wenzhe
kaust.personYantir, Hasan Erdem
kaust.personEltawil, Ahmed Mohamed
kaust.personSalama, Khaled N.

Files in this item

Publisher's Version/PDF

This item appears in the following Collection(s)

Show simple item record

This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.
Except where otherwise noted, this item's license is described as This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.