论文信息 - The dynamics of Learning Vector Quantization

The dynamics of Learning Vector Quantization

Winner-Takes-All (WTA) algorithms offer intuitive and pow- erful learning schemes such as Learning Vector Quantization (LVQ) and variations thereof, most of which are heuristically motivated. In this ar- ticle we investigate in an exact mathematical way the dynamics of differ- ent vector quantization (VQ) schemes including standard LVQ in simple, though relevant settings. We consider the training from high-dimensional data generated according to a mixture of overlapping Gaussians and the case of two prototypes. Simplifying assumptions allow for an exact de- scription of the on-line learning dynamics in terms of coupled differential equations. We compare the typical dynamics of the learning processes and the achievable generalization error.

[1] Thomas Villmann,et al. Generalized relevance learning vector quantization , 2002, Neural Networks.

[2] Michael Biehl,et al. Statistical Mechanics of On{line Learning and Generalization the Handbook of Brain Theory and Neural Networks , 2003 .

[3] David G. Stork,et al. Pattern Classification , 1973 .

[4] Klaus Obermayer,et al. Soft Learning Vector Quantization , 2003, Neural Computation.

[5] Michael Biehl,et al. A theoretical framework for analysing the dynamics of LVQ , 2004 .

[6] Thomas Villmann,et al. On the Generalization Ability of GRLVQ Networks , 2005, Neural Processing Letters.

[7] Panu Somervuo,et al. Self-Organizing Maps and Learning Vector Quantization for Feature Sequences , 1999, Neural Processing Letters.

[8] Michael A. Arbib,et al. The handbook of brain theory and neural networks , 1995, A Bradford book.

[9] J. Davenport. Editor , 1960 .

[10] Michael Biehl,et al. Dynamics of on-line competitive learning , 1997 .

[11] Klaus Obermayer,et al. Soft nearest prototype classification , 2003, IEEE Trans. Neural Networks.

[12] M. V. Velzen,et al. Self-organizing maps , 2007 .

[13] Shigeo Abe DrEng. Pattern Classification , 2001, Springer London.

[14] Christian Van den Broeck,et al. Statistical Mechanics of Learning , 2001 .

[15] R. Urbanczik,et al. SELF-AVERAGING AND ON-LINE LEARNING , 1998, cond-mat/9805339.