Design and Implementation of Parallel Counterpropagation Networks Using MPI

Authors:
Athanasios Margaris;Stavros Souravlas;Efthimios Kotsialos;Manos Roumeliotis
Affiliations:
University of Macedonia, Dept. of Applied Informatics, 156 Engatia Str., GR 540-06,Thessaloniki, Greece, e-mail: amarg@uom.gr, sourstav@uom.gr, ekots@uom.gr, manos@uom.gr;University of Macedonia, Dept. of Applied Informatics, 156 Engatia Str., GR 540-06,Thessaloniki, Greece, e-mail: amarg@uom.gr, sourstav@uom.gr, ekots@uom.gr, manos@uom.gr;University of Macedonia, Dept. of Applied Informatics, 156 Engatia Str., GR 540-06,Thessaloniki, Greece, e-mail: amarg@uom.gr, sourstav@uom.gr, ekots@uom.gr, manos@uom.gr;University of Macedonia, Dept. of Applied Informatics, 156 Engatia Str., GR 540-06,Thessaloniki, Greece, e-mail: amarg@uom.gr, sourstav@uom.gr, ekots@uom.gr, manos@uom.gr
Venue:
Informatica
Year:
2007

Citing 9
Cited 0

Neural networks: algorithms, applications, and programming techniques

Neural networks: algorithms, applications, and programming techniques
Simulating Artificial Neural Networks on Parallel Architectures

Computer - Special issue: neural computing: companion issue to Spring 1996 IEEE Computational Science & Engineering
Parallel programming with MPI

Parallel programming with MPI
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
MPI-The Complete Reference, Volume 1: The MPI Core

MPI-The Complete Reference, Volume 1: The MPI Core
A Scalable Parallel Formulation of the Backpropagation Algorithm for Hypercubes and Related Architectures

IEEE Transactions on Parallel and Distributed Systems
Development of neural models for the logistic equation and study of the neural based trajectories in the convergence, periodic, and chaotic regions

Neural, Parallel & Scientific Computations
A Library to Implement Neural Networks on MIMD Machines

Euro-Par '99 Proceedings of the 5th International Euro-Par Conference on Parallel Processing
Optimizing the parSOM Neural Network Implementation for Data Mining with Distributed Memory Systems and Cluster Computing

DEXA '00 Proceedings of the 11th International Workshop on Database and Expert Systems Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

The objective of this research is to construct parallel models that simulate the behavior of artificial neural networks. The type of network that is simulated in this project is the counterpropagation network and the parallel platform used to simulate that network is the message passing interface (MPI). In the next sections the counterpropagation algorithm is presented in its serial as well as its parallel version. For the latter case, simulation results are given for the session parallelization as well as the training set parallelization approach. Regarding possible parallelization of the network structure, there are two different approaches that are presented; one that is based to the concept of the intercommunicator and one that uses remote access operations for the update of the weight tables and the estimation of the mean error for each training stage.