SOM training optimization using triangle inequality

William Gozali; Ruli Manurung

doi:10.1007/978-3-319-28518-4_5

SOM training optimization using triangle inequality

Denny, William Gozali, Ruli Manurung

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Triangle inequality optimization is one of several strategies on the k- means algorithm that can reduce the search space in finding the nearest prototype vector. This optimization can also be applied towards Self-Organizing Maps training, particularly during finding the best matching unit in the batch training approach. This paper investigates various implementations of this optimization and measures the efficiency gained on various datasets, dimensions, maps, cluster size and density. Our experiments on synthetic and real life datasets show that the number of comparisons can be reduced to 24% and the running time can also reduced to between 63 and 87%.

Original language	English
Title of host publication	Advances in Self-Organizing Maps and Learning Vector Quantization - Proceedings of the 11th International Workshop WSOM 2016
Editors	Patrick O’Driscoll, Michael J. Mendenhall, Erzsébet Merényi
Publisher	Springer Verlag
Pages	61-71
Number of pages	11
ISBN (Print)	9783319285177
DOIs	https://doi.org/10.1007/978-3-319-28518-4_5
Publication status	Published - 2016
Event	11th International on Advances in Self-Organizing Maps and Learning Vector Quantization Workshop, WSOM 2016 - Houston, United States Duration: 6 Jan 2016 → 8 Jan 2016

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	428
ISSN (Print)	2194-5357

Conference

Conference	11th International on Advances in Self-Organizing Maps and Learning Vector Quantization Workshop, WSOM 2016
Country/Territory	United States
City	Houston
Period	6/01/16 → 8/01/16

Keywords

Implementation
Optimization
Self-Organizing Map
Triangle inequality

Access to Document

10.1007/978-3-319-28518-4_5

Cite this

Denny, Gozali, W., & Manurung, R. (2016). SOM training optimization using triangle inequality. In P. O’Driscoll, M. J. Mendenhall, & E. Merényi (Eds.), Advances in Self-Organizing Maps and Learning Vector Quantization - Proceedings of the 11th International Workshop WSOM 2016 (pp. 61-71). (Advances in Intelligent Systems and Computing; Vol. 428). Springer Verlag. https://doi.org/10.1007/978-3-319-28518-4_5

Denny ; Gozali, William ; Manurung, Ruli. / SOM training optimization using triangle inequality. Advances in Self-Organizing Maps and Learning Vector Quantization - Proceedings of the 11th International Workshop WSOM 2016. editor / Patrick O’Driscoll ; Michael J. Mendenhall ; Erzsébet Merényi. Springer Verlag, 2016. pp. 61-71 (Advances in Intelligent Systems and Computing).

@inproceedings{a2c1d102b58d41018236388f25f6495b,

title = "SOM training optimization using triangle inequality",

abstract = "Triangle inequality optimization is one of several strategies on the k- means algorithm that can reduce the search space in finding the nearest prototype vector. This optimization can also be applied towards Self-Organizing Maps training, particularly during finding the best matching unit in the batch training approach. This paper investigates various implementations of this optimization and measures the efficiency gained on various datasets, dimensions, maps, cluster size and density. Our experiments on synthetic and real life datasets show that the number of comparisons can be reduced to 24% and the running time can also reduced to between 63 and 87%.",

keywords = "Implementation, Optimization, Self-Organizing Map, Triangle inequality",

author = "Denny and William Gozali and Ruli Manurung",

note = "Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2016.; 11th International on Advances in Self-Organizing Maps and Learning Vector Quantization Workshop, WSOM 2016 ; Conference date: 06-01-2016 Through 08-01-2016",

year = "2016",

doi = "10.1007/978-3-319-28518-4_5",

language = "English",

isbn = "9783319285177",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer Verlag",

pages = "61--71",

editor = "Patrick O{\textquoteright}Driscoll and Mendenhall, {Michael J.} and Erzs{\'e}bet Mer{\'e}nyi",

booktitle = "Advances in Self-Organizing Maps and Learning Vector Quantization - Proceedings of the 11th International Workshop WSOM 2016",

address = "Germany",

}

Denny, Gozali, W & Manurung, R 2016, SOM training optimization using triangle inequality. in P O’Driscoll, MJ Mendenhall & E Merényi (eds), Advances in Self-Organizing Maps and Learning Vector Quantization - Proceedings of the 11th International Workshop WSOM 2016. Advances in Intelligent Systems and Computing, vol. 428, Springer Verlag, pp. 61-71, 11th International on Advances in Self-Organizing Maps and Learning Vector Quantization Workshop, WSOM 2016, Houston, United States, 6/01/16. https://doi.org/10.1007/978-3-319-28518-4_5

SOM training optimization using triangle inequality. / Denny; Gozali, William; Manurung, Ruli.
Advances in Self-Organizing Maps and Learning Vector Quantization - Proceedings of the 11th International Workshop WSOM 2016. ed. / Patrick O’Driscoll; Michael J. Mendenhall; Erzsébet Merényi. Springer Verlag, 2016. p. 61-71 (Advances in Intelligent Systems and Computing; Vol. 428).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - SOM training optimization using triangle inequality

AU - Denny, null

AU - Gozali, William

AU - Manurung, Ruli

N1 - Publisher Copyright: © Springer International Publishing Switzerland 2016.

PY - 2016

Y1 - 2016

N2 - Triangle inequality optimization is one of several strategies on the k- means algorithm that can reduce the search space in finding the nearest prototype vector. This optimization can also be applied towards Self-Organizing Maps training, particularly during finding the best matching unit in the batch training approach. This paper investigates various implementations of this optimization and measures the efficiency gained on various datasets, dimensions, maps, cluster size and density. Our experiments on synthetic and real life datasets show that the number of comparisons can be reduced to 24% and the running time can also reduced to between 63 and 87%.

AB - Triangle inequality optimization is one of several strategies on the k- means algorithm that can reduce the search space in finding the nearest prototype vector. This optimization can also be applied towards Self-Organizing Maps training, particularly during finding the best matching unit in the batch training approach. This paper investigates various implementations of this optimization and measures the efficiency gained on various datasets, dimensions, maps, cluster size and density. Our experiments on synthetic and real life datasets show that the number of comparisons can be reduced to 24% and the running time can also reduced to between 63 and 87%.

KW - Implementation

KW - Optimization

KW - Self-Organizing Map

KW - Triangle inequality

UR - http://www.scopus.com/inward/record.url?scp=84955281311&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-28518-4_5

DO - 10.1007/978-3-319-28518-4_5

M3 - Conference contribution

AN - SCOPUS:84955281311

SN - 9783319285177

T3 - Advances in Intelligent Systems and Computing

SP - 61

EP - 71

BT - Advances in Self-Organizing Maps and Learning Vector Quantization - Proceedings of the 11th International Workshop WSOM 2016

A2 - O’Driscoll, Patrick

A2 - Mendenhall, Michael J.

A2 - Merényi, Erzsébet

PB - Springer Verlag

T2 - 11th International on Advances in Self-Organizing Maps and Learning Vector Quantization Workshop, WSOM 2016

Y2 - 6 January 2016 through 8 January 2016

ER -

Denny, Gozali W, Manurung R. SOM training optimization using triangle inequality. In O’Driscoll P, Mendenhall MJ, Merényi E, editors, Advances in Self-Organizing Maps and Learning Vector Quantization - Proceedings of the 11th International Workshop WSOM 2016. Springer Verlag. 2016. p. 61-71. (Advances in Intelligent Systems and Computing). doi: 10.1007/978-3-319-28518-4_5

SOM training optimization using triangle inequality

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this