A parallel design and implementation for backpropagation neural network using MIMD architecture

A parallel design and implementation for backpropagation neural network using MIMD architecture

The paper illustrates a parallel backpropagation algorithm that depends upon a transputer network. Since the backpropagation algorithm is regarded as being communication intensive, a mechanism is developed to decrease the communication time overhead between different related processor elements. The...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Fathy, S.K., Syiam, M.M.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Algorithm design and analysis
Backpropagation algorithms
Character recognition
Computer architecture
Computer networks
Convergence
Neural networks
Neurons
Parallel algorithms
Training data
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The paper illustrates a parallel backpropagation algorithm that depends upon a transputer network. Since the backpropagation algorithm is regarded as being communication intensive, a mechanism is developed to decrease the communication time overhead between different related processor elements. The developed parallel backpropagation algorithm is applied to the problem of printed Arabic character recognition. The experimental results revealed that the speed up approaches the maximum value of 15.2 when a network of 16-transputers is utilized.
DOI:10.1109/MELCON.1996.551228