An incremental growing neural gas learns topologies

  title={An incremental growing neural gas learns topologies},
  author={Yann Prudent and A. Ennaji},
  journal={Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.},
  pages={1211-1216 vol. 2}
An incremental and growing network model is introduced which is able to learn the topological relations in a given set of input vectors by means of a simple Hebb-like learning rule. We propose a new algorithm for a SOM which can learn new input data (plasticity) without degrading the previously trained network and forgetting the old input data (stability). We report the validation of this model on experiments using a synthetic problem, the IRIS database and the handwriting digit recognition… CONTINUE READING
Highly Cited
This paper has 80 citations. REVIEW CITATIONS
39 Citations
15 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 39 extracted citations

81 Citations

Citations per Year
Semantic Scholar estimates that this publication has 81 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 15 references

Competitive Hebbian learning rule forms perfectly topology preserving maps

  • T. Martinetz
  • In Proc. ICANN'93,
  • 1993

A "Neural-Gas" network learns topologies

  • I T. Martinetz, K. Schulten
  • In Proc. ICANN,
  • 1991

Martinetz and K . Schulten . A " Neural - Gas " network learns topologies

  • Martinetz, K. Schulten
  • 1991

Similar Papers

Loading similar papers…