Title :
A neural network structure for vector quantizers
Author :
Huang, S.C. ; Huang, Y.F.
Author_Institution :
Dept. of Electr. Eng., Notre Dame Univ., IN, USA
Abstract :
A variable perturbation method for codebook design in vector quantization (VQ) is proposed. The resulting codebook can be used as the initial codebook in the implementation of the LBG (Line, Buzo, Gray, 1990) VQ algorithm. The proposed method is based on the concept of entropy implemented as a learning algorithm for a feedforward neural network. Such a neural network with the proposed learning algorithm can construct a codebook for input vectors with an unknown distribution without memorizing long training data
Keywords :
entropy; learning systems; neural nets; codebook design; entropy; feedforward neural network; learning algorithm; neural network structure; variable perturbation; vector quantizers; Computational complexity; Entropy; Euclidean distance; Feedforward neural networks; Intelligent networks; Iterative algorithms; Iterative methods; Neural networks; Perturbation methods; Vector quantization;
Conference_Titel :
Circuits and Systems, 1991., IEEE International Sympoisum on
Print_ISBN :
0-7803-0050-5
DOI :
10.1109/ISCAS.1991.176036
