DVQ: DYNAMIC VECTOR QUANTIZATION - AN INCREMENTAL LVQ

@inproceedings{Poirier1991DVQDV,
  title={DVQ: DYNAMIC VECTOR QUANTIZATION - AN INCREMENTAL LVQ},
  author={Franck Poirier and A. Ferrieux},
  year={1991}
}
Publisher Summary Neural networks (NN) are alternate tools for classification tasks. They have great generalization ability and work well for many real-world problems, such as acoustic-phonetic decoding in a speech recognition system. This chapter presents and evaluates a new version of the learning vector quantization (LVQ) algorithm called dynamic vector quantization (DVQ). The new method is based on an incremental procedure. DVQ consists in starting the training phase with only one… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 17 CITATIONS

Evolving Vector Quantization for Classification of On-Line Data Streams

  • 2008 International Conference on Computational Intelligence for Modelling Control & Automation
  • 2008
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A new algorithm for Kohonen layer learning with application to power system stability analysis

  • IEEE Trans. Systems, Man, and Cybernetics, Part B
  • 1997
VIEW 3 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Creating Evolving User Behavior Profiles Automatically

  • IEEE Transactions on Knowledge and Data Engineering
  • 2012
VIEW 1 EXCERPT
CITES METHODS