Stochastic Computing Convolutional Neural Network Architecture Reinvented for Highly Efficient Artificial Intelligence Workload on Field-Programmable Gate Array

Basit Öğe Kaydı
dc.authoridLee, Yang Yang/0000-0002-2497-7778
dc.contributor.authorLee, Yang Yang
dc.contributor.authorHalim, Zaini Abdul
dc.contributor.authorWahab, Mohd Nadhir Ab
dc.contributor.authorAlmohamad, Tarik Adnan
dc.date.accessioned2024-09-29T16:08:16Z
dc.date.available2024-09-29T16:08:16Z
dc.date.issued2024
dc.departmentKarabük Üniversitesien_US
dc.description.abstractStochastic computing (SC) has a substantial amount of study on application-specific integrated circuit (ASIC) design for artificial intelligence (AI) edge computing, especially the convolutional neural network (CNN) algorithm. However, SC has little to no optimization on field-programmable gate array (FPGA). Scaling up the ASIC logic without FPGA-oriented designs is inefficient, while aggregating thousands of bitstreams is still challenging in the conventional SC. This research has reinvented several FPGA-efficient function generator, and binary rectified linear unit, and successfully scaled and implemented a fully parallel CNN model on Kintex7 FPGA. The proposed SC hardware only compromises 0.14% accuracy compared to binary computing on the handwriting Modified National Institute of Standards and Technology classification task and achieved at least 99.72% energy saving per image feedforward and 31x more data throughput than modern hardware. Unique to SC, early decision termination pushed the performance baseline exponentially with minimum accuracy loss, making SC CNN extremely lucrative for AI edge computing but limited to classification tasks. The SC's inherent noise heavily penalizes CNN regression performance, rendering SC unsuitable for regression tasks.en_US
dc.description.sponsorshipUniversiti Sains Malaysia [RUI 1001/PELECT/8014152]en_US
dc.description.sponsorshipThis work was supported in part by the Universiti Sains Malaysia under Grant RUI 1001/PELECT/8014152.en_US
dc.identifier.doi10.34133/research.0307
dc.identifier.issn2096-5168
dc.identifier.issn2639-5274
dc.identifier.pmid38439995en_US
dc.identifier.scopus2-s2.0-85191020622en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.urihttps://doi.org/10.34133/research.0307
dc.identifier.urihttps://hdl.handle.net/20.500.14619/7446
dc.identifier.volume7en_US
dc.identifier.wosWOS:001229411600001en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.indekslendigikaynakPubMeden_US
dc.language.isoenen_US
dc.publisherAmer Assoc Advancement Scienceen_US
dc.relation.ispartofResearchen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectCircuitsen_US
dc.subjectDesignen_US
dc.titleStochastic Computing Convolutional Neural Network Architecture Reinvented for Highly Efficient Artificial Intelligence Workload on Field-Programmable Gate Arrayen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
PubMed İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu