Összesen 1 találat.
#/oldal:
Részletezés:
Rendezés:

1.

001-es BibID:BIBFORM032873
035-os BibID:WOS:000255232500111
Első szerző:Tisan, Alin
Cím:A generic control block for feedforward neural network with on-chipdelta rule learning algorithm / Alin Tisan, A. Buchman, Ş. Oniga, C. Gavrincea
Dátum:2007
Megjegyzések:In this paper we propose a method to implement in FPGA a feedforwardneural network with on-chip delta rule learning algorithm. For this, wehave develop a generic blocks designed in Mathworks' Simulinkenvironment, capable to generate the signals for controlling the neuronsfrom a neural network. The main characteristics of those blocks is itshigh reconfigurability that's makes it suitable for developing of ageneric controlling block capable to manage calculus function of neuronsfrom different layers. The properties of the block are set according tothe numbers of total layers, number of the neurons from the layers andthe number of layer from whom and in different Function Block Parameterswindows. The novelty of the proposed method resides in the possibilityto design neural networks with on-chip learning only with predefinedblock systems created in System Generator environment. The major benefitof this design methodology result from the possibility to create ahigher level design tools used to implement neural networks in logicalcircuits.
Tárgyszavak:Műszaki tudományok Villamosmérnöki tudományok konferenciacikk
Megjelenés:30th International Spring Seminar on Electronics Technology : Emerging Technologies for Electronics Packaging : May 9-13, 2007, Cluj-Napoca, Romania : conference proceedings. - (2007), p. 567-570. -
További szerzők:Buchman Attila (1957-) (villamosmérnök) Oniga István László (1960-) (villamosmérnök) Gavrincea, Ciprian
Internet cím:DOI
Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Rekordok letöltése1