Cell-Splitting Grid: A Self-Creating and Self-Organizing Neural Network

Abstract A new model of self-creating and self-organizing neural network, cell-splitting grid (CSG), is presented. In this proposed CSG algorithm, the neurons and their connections are created and organized on a 2-D plane according to the input data distribution. Compared with self-organizing map (SOM) and its other improved algorithms, the CSG algorithm has outperformed SOM and other SOM-related algorithms in vector quantization while maintaining relatively good topology preservation. This paper shows that CSG is a promising and an effective method especially for non-uniformly distributed data.

[1]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[2]  T. Kohonen Self-organized formation of topographically correct feature maps , 1982 .

[3]  Jennie Si,et al.  Dynamic topology representing networks , 2000, Neural Networks.

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

[5]  Bernd Fritzke,et al.  A Growing Neural Gas Network Learns Topologies , 1994, NIPS.

[6]  Hanan Samet,et al.  The Quadtree and Related Hierarchical Data Structures , 1984, CSUR.

[7]  Sang-Hui Park,et al.  Self-creating and organizing neural networks , 1994, IEEE Trans. Neural Networks.

[8]  R. Gray,et al.  Vector quantization , 1984, IEEE ASSP Magazine.

[9]  Tharam S. Dillon,et al.  Automated knowledge acquisition , 1994, Prentice Hall International series in computer science and engineering.

[10]  Bernd Fritzke,et al.  Growing cell structures--A self-organizing network for unsupervised and supervised learning , 1994, Neural Networks.

[11]  Risto Miikkulainen,et al.  Visualizing High-Dimensional Structure with the Incremental Grid Growing Neural Network , 1995, ICML.

[12]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[13]  B. Yegnanarayana,et al.  Artificial Neural Networks , 2004 .

[14]  Bala Srinivasan,et al.  Dynamic self-organizing maps with controlled growth for knowledge discovery , 2000, IEEE Trans. Neural Networks Learn. Syst..