Paper Info
Title
Fast sequential implementation of “neural-gas” network for vector quantization
Abstract
Although the “neural-gas” network proposed by Martinetz et al. in 1993 has been proven for its optimality in vector quantizer design and has been demonstrated to have good performance in time-series prediction, its high computational complexity (NlogN) makes it a slow sequential algorithm. We suggest two ideas to speedup its sequential realization: (1) using a truncated exponential function as its neighborhood function and (2) applying a new extension of the partial distance elimination method (PDE). This fast realization is compared with the original version of the neural-gas network for codebook design in image vector quantization. The comparison indicates that a speedup of five times is possible, while the quality of the resulting codebook is almost the same as that of the straightforward realization
Year
DOI
Venue
1998
10.1109/26.662634
IEEE Transactions on Communications
Keywords
Field
DocType
codebook design,sequential algorithm,image vector quantization,image coding,functional equations,speedup,time-series prediction,vector quantizer design,vector quantization.,vector quantisation,computational complexity,partial distance elimina- tion,index terms— neural-gas network,partial distance elimination method,neural-gas network,neighborhood function,performance,neural nets,truncated exponential function,fast sequential implementation,vector quantization,time series prediction,indexing terms,algorithm design and analysis,neural gas,exponential function,probability density function
Algorithm design,Linde–Buzo–Gray algorithm,Control theory,Computer science,Algorithm,Theoretical computer science,Vector quantization,Sequential algorithm,Quantization (signal processing),Neural gas,Codebook,Speedup
Journal
Volume
Issue
ISSN
46
3
0090-6778
Citations 
PageRank 
References 
8
1.14
6
Authors
2
Name
Order
Citations
PageRank
Clifford Sze-tsan Choy1758.03
Wan-Chi Siu22016210.10