An adaptive algorithm for training of a nearest neighbour (NN) classifier is developed in this paper. This learning rule has some similarity to the well-known LVQ method, but uses the nearest centroid neighbourhood concept to estimate optimal locations of the codebook vectors. The aim of this approach is to improve the performance of the standard LVQ algorithms when using a very small codebook. The behaviour of the learning technique proposed here is experimentally compared to those of the plain k-NN decision rule and the LVQ algorithms.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Learning vector quantization with alternative distance criteria


    Contributors:
    Sanchez, J.S. (author) / Pla, F. (author) / Ferri, F.J. (author)


    Publication date :

    1999-01-01


    Size :

    75770 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Learning Vector Quantization with Alternative Distance Criteria

    Sanchez, J. / Pla, F. / Ferri, F. et al. | British Library Conference Proceedings | 1999


    Vector Quantization Based on Dynamic Adjustment of Mahalanobis Distance

    Younis, K. S. / Rogers, S. K. / DeSimio, M. P. et al. | British Library Conference Proceedings | 1996


    Vector quantization based on dynamic adjustment of Mahalanobis distance

    Younis, K.S. / Rogers, S.K. / DeSimio, M.P. | IEEE | 1996


    Vector quantization with distance constraints for enhanced post-processing [2669-03]

    O'Rourke, T. P. / Stevenson, R. L. / SPIE | British Library Conference Proceedings | 1996


    MADDNESS Detector for MIMO Systems with Learning Vector Quantization

    Qian, Shuangyi / Gong, Shuaicong / Zhao, Chunming et al. | IEEE | 2024