Parameter quantization effects in Gaussian potential function neural networks

dc.contributor.authorKarakuş, Erkan
dc.contributor.authorÖğrenci, Arif Selçuk
dc.contributor.authorDündar, Günhan
dc.date.accessioned2019-06-28T11:11:57Z
dc.date.available2019-06-28T11:11:57Z
dc.date.issued2001
dc.departmentFakülteler, Mühendislik ve Doğa Bilimleri Fakültesi, Elektrik-Elektronik Mühendisliği Bölümüen_US
dc.description.abstractIn hardware implementations of Gaussian Potential Function Neural Networks (GPFNN) deviation from ideal network parameters is inevitable because of the techniques used for parameter storage and implementation of the functions electronically resulting in loss of accuracy. This loss in accuracy can be represented by quantization of the network parameters. In order to predict this effect theoretical approaches are proposed. One-input one-output GPFNN with one hidden layer have been trained as function approximators using the Gradient Descent algorithm. After the training the network parameters (means and standard deviations of the hidden units and the connection weights) are quantized up to 16-bits in order to observe the percentage error on network output stemming from parameter quantization. Simulation results are compared with the predictions of the theoretical approach. Consequently the behaviour of the network output has been given with combined and separate parameter quantizations. Moreover given the allowed percentage error for the network a method is proposed where the minimum number of bits required for quantization of each parameter could be determined based on the theoretical predictions.en_US]
dc.identifier.citation0
dc.identifier.endpage252
dc.identifier.isbn9608052262
dc.identifier.scopus2-s2.0-4944220484en_US
dc.identifier.scopusqualityN/A
dc.identifier.startpage247en_US
dc.identifier.urihttps://hdl.handle.net/20.500.12469/1744
dc.identifier.urihttps://www.semanticscholar.org/paper/Parameter-Quantization-Effects-in-Gaussian-Function-KARAKU-Ar/71acc1975e0e662088a34467acf19cd252044b90
dc.identifier.wosqualityN/A
dc.institutionauthorÖğrenci, Arif Selçuken_US
dc.language.isoenen_US
dc.publisherWorld Scientific and Engineering Academy and Societyen_US
dc.relation.journalAdvances in Neural Networks and Applicationsen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectGaussian potential function neural networksen_US
dc.subjectTrainingen_US
dc.subjectWeight quantizationen_US
dc.titleParameter quantization effects in Gaussian potential function neural networksen_US
dc.typeArticleen_US
dspace.entity.typePublication

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Parameter Quantization Effects in.pdf
Size:
198.08 KB
Format:
Adobe Portable Document Format
Description: