A case study of a distributed high-performance computing system for neurocomputing

We model here a distributed implementation of cross-stopping, a combination of cross-validation and early-stopping techniques, for the selection of the optimal architecture of feed-forward networks. Due to the very large computational demand of the method, we use the RAIN system (Redundant Array of...

Full description

Saved in:
Bibliographic Details
Published inJournal of systems architecture Vol. 46; no. 5; pp. 429 - 438
Main Authors Anguita, D., Boni, A., Parodi, G.
Format Journal Article
LanguageEnglish
Published Amsterdam Elsevier B.V 01.03.2000
Elsevier
Elsevier Sequoia S.A
Subjects
Applied sciences
Computers, microcomputers
Distributed computer systems
Distributed processing
Electronics
Exact sciences and technology
Hardware
Mathematical models
Neural networks
Neurocomputing
Statistical analysis
Statistical validation
Studies
Workstation cluster
Statistical validation
Neurocomputing
Workstation cluster
Backpropagation algorithm
Experimental result
Algorithm performance
Cross validation
Neural network
Distributed system
Distributed computing
Modeling
Implementation
Local network
Online AccessGet full text

Cover

More Information
Summary:We model here a distributed implementation of cross-stopping, a combination of cross-validation and early-stopping techniques, for the selection of the optimal architecture of feed-forward networks. Due to the very large computational demand of the method, we use the RAIN system (Redundant Array of Inexpensive workstations for Neurocomputing) as a target platform for the experiments and show that this kind of system can be effectively used for computational intensive neurocomputing tasks.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:1383-7621
1873-6165
DOI:10.1016/S1383-7621(99)00017-X