论文信息 - Topology Preservation in Self-Organizing Feature Maps: General Definition and Efficient Measurement

Topology Preservation in Self-Organizing Feature Maps: General Definition and Efficient Measurement

In this paper we present a new approach to the problem of measuring the topology preservation in SOFM. We introduce a precise definition of the meaning of that property and derive the so-called topographic function for its measuring based on the receptive fields of the neural units using explicitly the structure of the given data manifold.

Thomas Villmann | Thomas Martinetz | Ralf Der | J. Michael Herrmann

[1] Ralf Der,et al. A Novel Approach to Measure the Topology Preservation of Feature Maps , 1994 .

[2] Gilles Pagès,et al. Two or three things that we know about the Kohonen algorithm , 1994, ESANN.

[3] Jirí Benes,et al. On neural networks , 1990, Kybernetika.

[4] Teuvo Kohonen,et al. A Simple Paradigm for the Self-Organized Formation of Structured Feature Maps , 1982 .

[5] Stephane Zrehen,et al. Analyzing Kohonen Maps with Geometry , 1993 .

[6] Klaus Pawelzik,et al. Quantifying the neighborhood preservation of self-organizing feature maps , 1992, IEEE Trans. Neural Networks.

[7] Teuvo Kohonen,et al. The self-organizing map , 1990 .

[8] Leonid Kantorovich,et al. Funktionalanalysis in normierten Räumen , 1978 .

[9] Teuvo Kohonen,et al. Self-Organization and Associative Memory , 1988 .

[10] T. Martínez,et al. Competitive Hebbian Learning Rule Forms Perfectly Topology Preserving Maps , 1993 .

[11] Thomas Martinetz,et al. Topology representing networks , 1994, Neural Networks.