A Stochastic Computing Method For Generating Activation Functions in Multilayer Feedforward Neural Networks

Basit Öğe Kaydı
dc.authoridERSOY, Durmus/0000-0003-4303-3139
dc.contributor.authorErsoy, Durmuş
dc.contributor.authorErkmen, Burcu
dc.date.accessioned2025-03-26T17:34:43Z
dc.date.available2025-03-26T17:34:43Z
dc.date.issued2021
dc.departmentİstanbul Esenyurt Üniversitesi, Fakülteler, Mühendislik ve Mimarlık Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü
dc.description.abstractStochastic computing using basic arithmetic logic elements based on stochastic bit sequences provides very beneficial solutions in terms of speed and hardware cost, relative to deterministic calculation. Studies for the realization of tangent hyperbolic and exponential functions used in the development of activation functions in Artificial Neural Networks by stochastic methods exist in the literature. The techniques presented using state transitions on finite state machines were constructed on the basis of two different forms of finite state machines, one-dimensional (Linear) and two-dimensional. In this analysis, in terms of both error rate and circuit cost, the advantageous two-dimensional finite state machines based stochastic computing approach for tangent hyperbolic and exponential functions is presented. The presented approach is implemented on Field Programmable Gate Array and the results are given for hardware simulation. The dataset used for the classification process in a decentralized smart grid control has been applied to the multilayer feedforward neural network and deterministic computing, for the stability classification which is carried out separately with the linear finite state machines based stochastic computing and the proposed 2D finite state machines based stochastic computing methods.
dc.identifier.doi10.5152/electr.2021.21043
dc.identifier.endpage+
dc.identifier.issn2619-9831
dc.identifier.issue3
dc.identifier.scopus2-s2.0-85126081907
dc.identifier.scopusqualityQ3
dc.identifier.startpage376
dc.identifier.trdizinid486148
dc.identifier.urihttps://doi.org/10.5152/electr.2021.21043
dc.identifier.urihttps://search.trdizin.gov.tr/tr/yayin/detay/486148
dc.identifier.urihttps://hdl.handle.net/20.500.14704/859
dc.identifier.volume21
dc.identifier.wosWOS:000697292900008
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakTR-Dizin
dc.language.isoen
dc.publisherIstanbul Univ-Cerrahpasa
dc.relation.ispartofElectrica
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_WOS_20250326
dc.subjectField Programmable Gate Array; finite state machine; multilayer feedforward neural networks; stochastic activation function; stochastic computing
dc.titleA Stochastic Computing Method For Generating Activation Functions in Multilayer Feedforward Neural Networks
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Mühendislik ve Mimarlık Fakültesi Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu
TR-Dizin İndeksli Yayınlar Koleksiyonu