A Parallel Implementation of a Growing SOM Promoting Independent Neural Networks over Distributed Input Space

Self-organizing maps can discover topological and multidimensional patterns using a variety of methods. We apply a parallel algorithm proposed by the authors (ParaSOM), which yields closer and denser approximations than other methods in a fraction of iterations, to a two-dimensional pattern in a parallel environment to demonstrate a high degree of neuron independence. In a second implementation, pieces of a two-dimensional input space are distributed over a network and processed by independent ParaSOM algorithms.

[1]  Bernd Fritzke.  Growing Grid — a self-organizing network with constant neighborhood range and adaptation strength , 1995, Neural Processing Letters.

[2]  E. Oja,et al.  Clustering Properties of Hierarchical Self-Organizing Maps , 1992 .

[3]  Jouko Lampinen,et al.  Clustering properties of hierarchical self-organizing maps , 1992, Journal of Mathematical Imaging and Vision.

[4]  Jon G. Solheim,et al.  Wavefront implementation of Self Organizing Maps on RENNS , 1995 .

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

[6]  FritzkeBernd.  Growing cell structuresa self-organizing network for unsupervised and supervised learning , 1994 .

[7]  Iren Valova,et al.  A growing parallel self-organizing map for unsupervised learning , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[8]  Andreas Rauber,et al.  The growing hierarchical self-organizing map , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

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

[10]  George Karypis,et al.  Introduction to Parallel Computing , 1994 .

[11]  Christoph von der Malsburg,et al.  Network self-organization , 1990 .

[12]  Iren Valova,et al.  A parallel algorithm for growing , unsupervised , self-organizing maps utilizing specialized regions of influence and neuron inertia , 2005 .

[13]  Robert Michael Kirby,et al.  Parallel Scientific Computing in C++ and MPI - A Seamless Approach to Parallel Algorithms and their Implementation , 2003 .

[14]  Stan Openshaw,et al.  A parallel Kohonen algorithm for the classification of large spatial datasets , 1996 .

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

[16]  Iren Valova,et al.  ParaGro: a learning algorithm for growing parallel self-organizing maps with any input/output dimensions , 2005, Int. J. Gen. Syst..

[17]  RauberA.,et al.  The growing hierarchical self-organizing map , 2002 .

[18]  Chia-Jiu Wang,et al.  Parallelizing the self-organizing feature map on multiprocessor systems , 1991, Parallel Comput..

[19]  Iren Valova,et al.  A parallel growing architecture for self-organizing maps with unsupervised learning , 2005, Neurocomputing.

[20]  Li Weigang.  A Study of Parallel Self-Organizing Map , 1998 .

[21]  Tomas Nordström,et al.  Designing parallel computers for self organizing maps , 1991 .