Neural maps and topographic vector quantization

  title={Neural maps and topographic vector quantization},
  author={Hans-Ulrich Bauer and J. Michael Herrmann and Thomas Villmann},
  journal={Neural networks : the official journal of the International Neural Network Society},
  volume={12 4-5},
Neural maps combine the representation of data by codebook vectors, like a vector quantizer, with the property of topography, like a continuous function. While the quantization error is simple to compute and to compare between different maps, topography of a map is difficult to define and to quantify. Yet, topography of a neural map is an advantageous property, e.g. in the presence of noise in a transmission channel, in data visualization, and in numerous other applications. In this article we… CONTINUE READING
Highly Cited
This paper has 104 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 56 citations

105 Citations

Citations per Year
Semantic Scholar estimates that this publication has 105 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 42 references

An Index of Topological Preserva- tion and its Application to Self-Organizing Feature Maps

  • J. C. Bezdek, N. R. Pal
  • Proc. IJCNN'93, Int. Joint Conf. on Neural…
  • 1995
Highly Influential
8 Excerpts

Martinetz , General De nition of Topology Preservation in Self - Organizing Feature Maps and the Topographic Function for its Measurement

  • R. Der Th. Villmann, M. Herrmann, Th.
  • 1997

Constructing Principal Manifolds in Sparse Data Sets by Self-Organizing Maps with Self-Regulating Neighborhood Width

  • R. Der, G. Balzuweit, M. Herrmann
  • In: Proc. ICNN'96 Wash- ington, IEEE, 480-483
  • 1996
1 Excerpt

Controlling the Magni ca- tion Factor of Self-Organizing Feature Maps

  • H.-U. Bauer, R. Der, M. Herrmann
  • Neural Computa- tion 8, 757-771
  • 1995
1 Excerpt