www.uhasselt.be
DSpace

Document Server@UHasselt >
Research >
Research publications >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/23504

Title: A Fast Self-Organizing Map Algorithm for Handwritten Digit Recognition
Authors: Wang, Yimu
Peyls, Alexander
Pan, Yun
Claesen, Luc
Yan, Xiaolang
Issue Date: 2013
Publisher: Springer
Citation: Park, James J. (Jong Hyuk); Kee-Yin Ng, Joseph; Jeong, Hwa-Young; Waluyo, Borgy (Ed.). Multimedia and Ubiquitous Engineering, Springer,p. 177-183
Series/Report: Lecture Notes in Electrical Engineering
Series/Report no.: 240
Abstract: This paper presents a fast version of the self-organizing map (SOM) algorithm, which simplifies the weight distance calculation, the learning rate function and the neighborhood function by removing complex computations. Simplification accelerates the training process in software simulation and is applied in the field of handwritten digit recognition. According to the evaluation results of the software prototype, a 15–20 % speed-up in the runtime is obtained compared with the conventional SOM. Furthermore, the fast SOM accelerator can recognize over 81 % of handwritten digit test samples correctly, which is slightly worse than the conventional SOM, but much better than other simplified SOM methods.
URI: http://hdl.handle.net/1942/23504
DOI: 10.1007/978-94-007-6738-6_23
ISBN: 9789400767379
ISSN: 1876-1100
Category: C1
Type: Proceedings Paper
Appears in Collections: Research publications

Files in This Item:

Description SizeFormat
Published version1.76 MBAdobe PDF

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.