Multi-reference neighborhood search for vector quantization by neural network prediction and self-organized feature map

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
PublisherIEEE
Pages1898-1902
Volume4
Publication statusPublished - 1995

Publication series

Name
Volume4

Conference

TitleProceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6)
CityPerth, Aust
Period27 November - 1 December 1995

Abstract

Reference Neighbor Search (RNS) is a new technique for fast searching of vector quantization (VQ). However, the optimal performance is not guaranteed and the performance is greatly affected by the selection of reference point. In this research, we employed the Kohonen Self Organized Feature Map to generate codebook of high degree of neighborhood and Multi-Layer Perceptron (MLP) neural network to adaptively predict the reference. The predicted reference is closer to the input, thus the search distance will be reduced. Together with multiple queues and a look up table, the number of searches is significantly reduced while maintaining optimal performance.

Citation Format(s)

Multi-reference neighborhood search for vector quantization by neural network prediction and self-organized feature map. / Chan, K. W.; Chan, K. L.
IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 4 IEEE, 1995. p. 1898-1902.

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review