Title :
Modeling of intelligent calculations in cubic network of workstations
Author :
N. Adam;L. Vokorokos;B. Mados
Author_Institution :
Technical university of Ko?ice/Department of Computers and Informatics, Slovakia
Abstract :
Article describes model of computation with feedforward multilayer neural network implemented in the network of workstations with cubic topology. Presented computation model is based on parallel error backpropagation algorithm with regard to characteristics of simulations implementation architecture. Effectivity of parallel implementation of feedforward multilayer neural network is represented trough the cost of computation in parallel environment of workstations. Designed computation model allows formally describe components of parallel implementation of neural network. Model provides mathematical instrument for verification of performance, used in simulation of feedforward multilayer neural network on specified hardware platform.
Keywords :
"Intelligent networks","Workstations","Multi-layer neural network","Computational modeling","Neural networks","Computer networks","Feedforward neural networks","Concurrent computing","Network topology","Backpropagation algorithms"
Conference_Titel :
Applied Machine Intelligence and Informatics, 2009. SAMI 2009. 7th International Symposium on
Print_ISBN :
978-1-4244-3801-3
DOI :
10.1109/SAMI.2009.4956627
