Use of Kohonen's self-organizing network as a pre-quantizer
DSpace at IIT Bombay
View Archive InfoField | Value | |
Title |
Use of Kohonen's self-organizing network as a pre-quantizer
|
|
Creator |
KHAPARDE, SA
GANDHI, HARISH |
|
Subject |
quantisation
self-organising feature maps |
|
Description |
Kohonen's network has the ability to achieve near optimal quantization of the input space. The Kohonen's training algorithm adapts very quickly to the input space and requires much less computation. Many experiments are carried out to compare the performance of the LBG algorithm and the Kohonen's algorithm. The variables used are the dimensionality of the input space and the level of organization. The results are found to confirm the faster adaptation of the Kohonen's algorithm although the final distortion levels are slightly higher. A combination of the two approaches is suggested to achieve lower distortion values with less training.
|
|
Publisher |
IEEE
|
|
Date |
2008-12-10T06:37:07Z
2011-11-28T08:31:14Z 2011-12-15T09:57:41Z 2008-12-10T06:37:07Z 2011-11-28T08:31:14Z 2011-12-15T09:57:41Z 1993 |
|
Type |
Article
|
|
Identifier |
Proceedings of the IEEE International Conference on Neural Networks (V 2), San Francisco, USA, 28 March -1 April, 1993, 967-971
0-7803-0999-5 10.1109/ICNN.1993.298688 http://hdl.handle.net/10054/252 http://dspace.library.iitb.ac.in/xmlui/handle/10054/252 |
|
Language |
en
|
|