Lazy Self-Organizing Map and its behaviors

  title={Lazy Self-Organizing Map and its behaviors},
  author={Taku Haraguchi and Haruna Matsushita and Yoshifumi Nishio},
  journal={2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)},
  • Taku Haraguchi, H. Matsushita, Y. Nishio
  • Published 2008
  • Computer Science
  • 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)
The Self-Organizing Map (SOM) is a famous algorithm for the unsupervised learning and visualization introduced by Teuvo Kohonen. This study proposes the Lazy Self-Organizing Map (LSOM) algorithm which reflects the world of worker ants. In LSOM, three kinds of neurons exist: worker neurons, lazy neurons and indecisive neurons. We apply LSOM to various input data set and confirm that LSOM can obtain a more effective map reflecting the distribution state of the input data than the conventional SOM… Expand
Behaviors of Lazy Self-Organizing Map Considering Lazy-Neuron Rate
The Self-Organizing Map (SOM) is unsupervised neural networks introduced by Kohonen. The SOM attracts attentions for clustering in these years. In the previous study, we have proposed the LazyExpand
Lazy Self-Organizing Map Considering Lazy-Neuron Rate for Effective Self-Organization
An improved LSOM, whose learning rate depends on each neuron’s character, lazy-neuron rate and time is proposed and applied to various input data set and investigated its effectiveness using three measurements. Expand


Self-Organizing Maps
  • T. Kohonen
  • Computer Science
  • Springer Series in Information Sciences
  • 1995
The mathematical preliminaries, background, basic ideas, and implications of the Self-Organising Map algorithm are expounded in a manner which is accessible without prior expert knowledge. Expand
Rival-Model Penalized Self-Organizing Map
A novel rival-model penalized self-organizing map (RPSOM) learning algorithm that adaptively chooses several rivals of the best-matching unit (BMU) and penalizes their associated models, i.e., those parametric real vectors with the same dimension as the input vectors. Expand
Clustering of the self-organizing map
The two-stage procedure--first using SOM to produce the prototypes that are then clustered in the second stage--is found to perform well when compared with direct clustering of the data and to reduce the computation time. Expand
Optimization of group behavior on cellular robotic system in dynamic environment
The authors propose a concept of self-recognition for the decision making of the behavior in a group, and shows the learning and adaptation strategy for the group behavior, and presents some simulation results. Expand
Clustering with SOM: U*C
  • Proc. Workshop on Self- Organizing Maps,
  • 2005