Advertisement

Evaluation-Based Topology Representing Network for Accurate Learning of Self-Organizing Relationship Network

  • Takeshi Yamakawa
  • Keiichi Horio
  • Takahiro Tanaka
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4232)

Abstract

A Self-Organizing Relationship (SOR) network approximates a desirable input-output (I/O) relationship of a target system using I/O vector pairs and their evaluations. However, in the case where the topology of the network is different from that of the data set, the SOR network cannot precisely represent the topology of the data set and generate desirable outputs, because topology of the SOR network is fixed in one- or two dimensional surface during learning. On the other hand, a Topology Representing Network (TRN) precisely represents the topology of the data set by a graph using the Competitive Hebbian Learning. In this paper, we propose a novel method which represents topology of the data set with evaluation by creating a fusion of SOR network and TRN.

Keywords

Weight Vector Target System Connection Strength Desirable Output Execution Mode 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Yamakawa, T., Horio, K.: Self-Organizing Relationship (SOR) Network. IEICE Trans. on Fandamentals E82-A, 1674–1677 (1999)Google Scholar
  2. 2.
    Furukawa, T., Sonoh, S., Horio, K., Yamakawa, T.: Batch Learning Algorithm of SOM with Attractive and Repulsive Data. In: Proc. of Workshop on Self-Organizing Maps (WSOM), pp. 413–420 (2005)Google Scholar
  3. 3.
    Martinetz, T., Schulten, K.: Topology Representing Networks. Neural Networks 7, 507–522 (1994)CrossRefGoogle Scholar
  4. 4.
    Martinetz, T., Berkovich, S., Schulten, K.: Neural-Gas Network for Vector Quantization and its Application to Time-Series Prediction. IEEE Trans. on Neural Networks 4, 558–569 (1993)CrossRefGoogle Scholar
  5. 5.
    Martinetz, T.: Competitive Hebbian learning rule forms perfectly topology preserving maps. In: Proc. of Int. Conf. on Artificial Neural Networks (ICANN), pp. 427–434 (1993)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Takeshi Yamakawa
    • 1
  • Keiichi Horio
    • 1
  • Takahiro Tanaka
    • 2
  1. 1.Graduate school of Life Science and Systems EngineeringKyushu Institute of TechnologyFukuokaJapan
  2. 2.FANUC LTDOshino, YamanashiJapan

Personalised recommendations