A bridge between two paradigms for parallelism: neural networks and general purpose MIMD computers

Boniface, Yann; Alexandre, Frédéric; Vialle, Stéphane

doi:10.1109/ijcnn.1999.833453

Cited by 7 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We are currently working on a MPI-based implementation to create an optimal version for this architecture. Overall, our results compare favourably with the performance reported in [2], both in terms of spead-up and execution time. …”

Section: Som Clustering Evaluationsupporting

confidence: 69%

parSOM: a parallel implementation of the self-organizing map exploiting cache effects: making the SOM fit for interactive high-performance data analysis

Rauber

Tomsich

Merkl

2000

Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challeng

View full text Add to dashboard Cite

A large number of applications has shown, that the self-organizing map is a prominent unsupervised neural network model for high-dimensional data analysis. However, the high execution times required to train the map put a limit to its use in many application domains, where either very large datasets are encountered and/or interactive response times are required.In order to provide interactive response times during data analysis we developed the ,.3OM, a softwarebased parallel implementation of the self-organizing map Parallel execution reduces the training time to a large degree, with an even higher speedup obtained by using the resulting cache effects. We demonstrate the scalability of the ,.,SOM system and the speed-up obtained on different architectures using an example from high-dimensional text data classification.

show abstract

Section: Som Clustering Evaluationsupporting

confidence: 69%

parSOM: a parallel implementation of the self-organizing map exploiting cache effects: making the SOM fit for interactive high-performance data analysis

Rauber

Tomsich

Merkl

2000

Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challeng

View full text Add to dashboard Cite

show abstract

“…These wide varieties of examples demonstrate that considerable effort has been placed on applying these multivariate tools. Optimizations to par SOM, a software-based parallel implementation of the SOM was first introduced by Tomsich et al (2000) which provides a better performance compared to other implementation attempts such as the one reported in Boniface et al (1999).…”

Section: Introductionmentioning

confidence: 99%

“…Successful applications have been reported in different industrial processes such as:start‐up operation in a steel casting process in Zhang and Dudzic (2006);operation of a copper smelter in Ross (1988);monitoring product quality in the food processing industry both in Sheridan et al (2006) and Yu et al (2003);monitoring of combustion processes in Yu and MacGregor (2004);remote sensing image analysis in Villmann et al (2003);discovering operational strategies in the refinery fluid catalytic cracking process in Sebzalli and Wang (2001);medical image analysis in Li et al (2006);genomics data modelling in Eriksson et al (2004);increase pharmaceutical data process understanding in Jorgensen et al (2004);adaptive modelling of an offset lithographic printing process in Englund and Verikas (2007); anddynamic modelling of the maize drying process in Liu et al (2006).These wide varieties of examples demonstrate that considerable effort has been placed on applying these multivariate tools. Optimizations to par SOM, a software‐based parallel implementation of the SOM was first introduced by Tomsich et al (2000) which provides a better performance compared to other implementation attempts such as the one reported in Boniface et al (1999).…”

Section: Introductionmentioning

confidence: 99%

Application of Self Organizing Map (SOM) to model a machining process

Saraee

Moosavi

Rezapour

2011

Journal of Manufacturing Technology Management

View full text Add to dashboard Cite

Purpose-This paper aims to present a practical application of Self Organizing Map (SOM) and decision tree algorithms to model a multi-response machining process and to provide a set of control rules for this process. Design/methodology/approach-SOM is a powerful artificial neural network approach used for analyzing and visualizing high-dimensional data. Wire electrical discharge machining (WEDM) process is a complex and expensive machining process, in which there are a lot of factors having effects on the outputs of the process. In this work, after collecting a dataset based on a series of designed experiments, the paper applied SOM to this dataset in order to analyse the underlying relations between input and output variables as well as interactions between input variables. The results are compared with the results obtained from decision tree algorithm. Findings-Based on the analysis of the results obtained, the paper extracted interrelationships between variables as well as a set of control rules for prediction of the process outputs. The results of the new experiments based on these rules, clearly demonstrate that the paper's predictions are valid, interesting and useful. Originality/value-To the best of the authors' knowledge, this is the first time SOM and decision tree has been applied to the WEDM process successfully.

show abstract

Optimizing the parSOM neural network implementation for data mining with distributed memory systems and cluster computing

Tomsich

Rauber²,

Merkl³

Proceedings 11th International Workshop on Database and Expert Systems Applications

View full text Add to dashboard Cite

The self-organizing map is a prominent unsupervised neural network model which lends itself to the analysis of high-dimensional input data and data mining applications. However; the high execution times required to train the map put a limit to its application in many high-performance data analysis application domains.In this paper we discuss the ,,&OM imp!ementation, a software-based parallel implementation of the seljorganizing map, and its optimization for the analysis of high-dimensional input data using distributed memory systems and clusters. The original r,&OM algorithm scales very well in a parallel execution environment with low communication latencies and exploits parallelism to cope with memory latencies. However it suffers from poor scalability on distributed memory computers. We present optimizations to further decouple the subprocesses, simplifi the conimunication model and improve the portabilit?, of the sj'stem. 0-7695-0680-1/00 $10.00 0 2000 IEEE

show abstract

A bridge between two paradigms for parallelism: neural networks and general purpose MIMD computers

Cited by 7 publications

References 6 publications

parSOM: a parallel implementation of the self-organizing map exploiting cache effects: making the SOM fit for interactive high-performance data analysis

parSOM: a parallel implementation of the self-organizing map exploiting cache effects: making the SOM fit for interactive high-performance data analysis

Application of Self Organizing Map (SOM) to model a machining process

Optimizing the parSOM neural network implementation for data mining with distributed memory systems and cluster computing

Contact Info

Product

Resources

About