• English
    • Türkçe
  • English 
    • English
    • Türkçe
  • Login
View Item 
  •   DSpace Home
  • Araştırma Çıktıları / Scopus
  • Araştırma Çıktıları / Scopus
  • View Item
  •   DSpace Home
  • Araştırma Çıktıları / Scopus
  • Araştırma Çıktıları / Scopus
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Parameter quantization effects in Gaussian potential function neural networks

Thumbnail
View/Open
Parameter Quantization Effects in.pdf (198.0Kb)
Date
2001
Author
Karakuş, Erkan
Öǧrenci, Arif Selçuk
Dündar, Günhan
Abstract
In 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.

Source

Advances in Neural Networks and Applications

Pages

247-252

URI

https://hdl.handle.net/20.500.12469/1744
https://www.semanticscholar.org/paper/Parameter-Quantization-Effects-in-Gaussian-Function-KARAKU-Ar/71acc1975e0e662088a34467acf19cd252044b90

Collections

  • Araştırma Çıktıları / Scopus [1565]
  • Elektrik-Elektronik Mühendisliği / Electrical - Electronics Engineering [321]

Keywords

Gaussian potential function neural networks
Training
Weight quantization

Share


DSpace software copyright © 2002-2015  DuraSpace
Contact Us | Send Feedback
Theme by 
@mire NV
 

 

Browse

All of DSpaceCommunities & CollectionsBy Issue DateBy AuthorsBy TitlesBy SubjectsBy TypesBy LanguagesBy DepartmentsBy PublishersBy KHAS AuthorsBy Access TypesThis CollectionBy Issue DateBy AuthorsBy TitlesBy SubjectsBy TypesBy LanguagesBy DepartmentsBy PublishersBy KHAS AuthorsBy Access Types

My Account

LoginRegister

Statistics

View Google Analytics Statistics

DSpace software copyright © 2002-2015  DuraSpace
Contact Us | Send Feedback
Theme by 
@mire NV