By Topic

Multilayer perceptron and vector quantization

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Wang Xinwen ; DSP Lab., Southeast Univ., Jiangsu, China ; Zou Lihe ; He Zhenya

The exponential encoding complexity has been the bottleneck drawback of vector quantization (VQ) in its applications. A kind of neural network multilayer perceptron (MLP) is introduced to attack the bottleneck. Based on the analysis of the VQ structure and the function of the MLP, an important conclusion on the relationship between the task and the scale required by it is drawn so that the two-layer MLP is adequate for VQ encoding or recognition. Simulation experiments are presented to test the theoretical analysis

Published in:

Industrial Electronics, Control and Instrumentation, 1991. Proceedings. IECON '91., 1991 International Conference on

Date of Conference:

28 Oct-1 Nov 1991