Vector quantization of neural networks

Author

Chu, W.C. ; Bose, N.K.

Author_Institution

Dept. of Electr. Eng., Pennsylvania State Univ., University Park, PA, USA

Volume

9

Issue

6

fYear

1998

fDate

11/1/1998 12:00:00 AM

Firstpage

1235

Lastpage

1245

Abstract

The problem of vector quantizing the parameters of a neural network is addressed, followed by a discussion of different algorithms applicable for quantizer design. Optimal, as well as several suboptimal quantization schemes are described. Simulations involving nonlinear prediction of speech signals are presented to compare the performance of different quantization techniques. Performance evaluation conducted uncover the tradeoffs in implementational complexity. Among the three examined suboptimal quantization schemes, it is shown that the multistage quantizer offers the best tradeoff between complexity and performance

Keywords

multilayer perceptrons; prediction theory; speech processing; unsupervised learning; vector quantisation; implementational complexity; multistage quantizer; neural networks; nonlinear prediction; optimal quantization schemes; performance evaluation; speech signals; suboptimal quantization schemes; vector quantization; Algorithm design and analysis; Decoding; Multidimensional signal processing; Multidimensional systems; Neural networks; Predictive models; Speech analysis; Speech coding; Speech processing; Vector quantization;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.728372

Filename

728372