COMPETITIVE LEARNING ALGORITHMS FOR VECTOR QUANTIZATION

被引：451

作者：

AHALT, SC

KRISHNAMURTHY, AK

CHEN, PK

MELTON, DE

机构：

[1] Ohio State University, Columbus

来源：

NEURAL NETWORKS | 1990年 / 3卷 / 03期

关键词：

Encoding; Neural networks; Speech; Vector quantization;

D O I：

10.1016/0893-6080(90)90071-R

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We compare a number of training algorithms for competitive learning networks applied to the problem of vector quantization for data compression. A new competitive-learning algorithm based on the "conscience" learning method is introduced. The performance of competitive learning neural networks and traditional non-neural algorithms for vector quantization is compared. The basic properties of the algorithms are discussed and we present a number of examples that illustrate their use. The new algorithm is shown to be efficient and yields near-optimal results. This algorithm is used to design a vector quantizer for a speech database. We conclude with a discussion of continuing work. © 1990.

引用

页码：277 / 290

页数：14

共 31 条

[11] APPLICATIONS OF COUNTERPROPAGATION NETWORKS
HECHTNIELSEN, R
[J]. NEURAL NETWORKS, 1988, 1 (02) : 131 - 139
[12] AN INTRODUCTION TO NEURAL COMPUTING
KOHONEN, T
[J]. NEURAL NETWORKS, 1988, 1 (01) : 3 - 16
[13] KOHONEN T, 1988, 1ST ANN INNS M BOST, P303
[14] Kohonen T., 1988, SELF ORG ASS MEMORY
[15] Kohonen T., 1984, SELF ORG ASS MEMORY
[16] ALGORITHM FOR VECTOR QUANTIZER DESIGN
LINDE, Y
BUZO, A
GRAY, RM
[J]. IEEE TRANSACTIONS ON COMMUNICATIONS, 1980, 28 (01) : 84 - 95
[17] Lippmann R. P., 1988, Computer Architecture News, V16, P7, DOI [10.1109/MASSP.1987.1165576, 10.1145/44571.44572]
[18] Lloyd S., 1982, IEEE T INFORMATION T, V28, P129, DOI DOI 10.1109/TIT.1982.1056489
[19] VECTOR QUANTIZATION IN SPEECH CODING
MAKHOUL, J
ROUCOS, S
GISH, H
[J]. PROCEEDINGS OF THE IEEE, 1985, 73 (11) : 1551 - 1588
[20] MATSUYAMA Y, 1988, J NEURAL NETWORKS

← 1 2 3 4 →