Evolutionary self-organizing map

Maiga Chang, Horng Jyh Yu, Jia Sheng Heh

Research output: Contribution to conferencePaperpeer-review

5 Citations (Scopus)


Extending Kohonen's SOM, this paper proposes one kind of dynamically growing neural network, called Evolutionary SOM (ESOM). Firstly, the output layer of SOM is represented by a so-called neighborhood graph, where nodes are neurons' weights and edges are the neighborhood relationships of SOM. Then two basic differentiation operations, node differentiation and edge differentiation, are proposed for network differentiation. As Nature's evolution, each generation of ESOM includes several species of neural nets and the survivors of competition will differentiate to the next generation. This kind of evolution is implemented as two new modules of ESOM, in addition to Kohonen's SOM toolbox in Matlab. A cross pattern with 1000 data points is taken as example. The results show that there are a large quantity of unnecessary neurons in Kohonen's SOMs; whereas, the resultant ESOM has much less size and better fitness to training input.

Original languageEnglish
Number of pages6
Publication statusPublished - 1998
EventProceedings of the 1998 IEEE International Joint Conference on Neural Networks. Part 1 (of 3) - Anchorage, AK, USA
Duration: 4 May 19989 May 1998


ConferenceProceedings of the 1998 IEEE International Joint Conference on Neural Networks. Part 1 (of 3)
CityAnchorage, AK, USA


Dive into the research topics of 'Evolutionary self-organizing map'. Together they form a unique fingerprint.

Cite this