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

K. W. Chan; K. L. Chan

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

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

Overview

View graph of relations

Author(s)

K. W. Chan
K. L. Chan

Related Research Unit(s)

City University of Hong Kong

Detail(s)

Original language	English
Title of host publication	IEEE International Conference on Neural Networks - Conference Proceedings
Publisher	Institute of Electrical and Electronics Engineers, Inc.
Pages	1898-1902
Volume	4
Publication status	Published - 1995

Publication series

Name
Volume	4

Conference

Title	Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6)
City	Perth, Aust
Period	27 November - 1 December 1995

Link(s)

	Check@CityULib
Link to Scopus	https://www.scopus.com/record/display.uri?eid=2-s2.0-0029521623&origin=recordpage
Permanent Link	https://scholars.cityu.edu.hk/en/publications/publication(edca9e40-0c68-443a-bd2b-ff8106885611).html

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.

Fingerprint

Publication fingerprints text

100

Search Neighborhood Engineering

100

Vector Quantization Engineering

100

Optimal Performance Engineering

100

Prediction Network Engineering

100

Neural Network Computer Science

100

Feature Map Computer Science

Code Book Engineering

Lookup Table Engineering

Reference Point Engineering

Perceptron Engineering

Full Fingerprint ›

Citation Format(s)

[ RIS ] [ BibTeX ]

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 Institute of Electrical and Electronics Engineers, Inc., 1995. p. 1898-1902.

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

Chan, KW & Chan, KL 1995, Multi-reference neighborhood search for vector quantization by neural network prediction and self-organized feature map. in IEEE International Conference on Neural Networks - Conference Proceedings. vol. 4, Institute of Electrical and Electronics Engineers, Inc., pp. 1898-1902, Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6), Perth, Aust, 27/11/95.

Chan, K. W., & Chan, K. L. (1995). Multi-reference neighborhood search for vector quantization by neural network prediction and self-organized feature map. In IEEE International Conference on Neural Networks - Conference Proceedings (Vol. 4, pp. 1898-1902). Institute of Electrical and Electronics Engineers, Inc..

Chan KW, Chan KL. Multi-reference neighborhood search for vector quantization by neural network prediction and self-organized feature map. In IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 4. Institute of Electrical and Electronics Engineers, Inc. 1995. p. 1898-1902

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