Title :
On a novel adaptive self organizing network
Author :
Kawahara, Shingo ; Saito, Toshimichi
Author_Institution :
Dept. of Electr. Eng., Hosei Univ., Tokyo, Japan
Abstract :
In this paper a new algorithm is presented in order to overcome the stability vs. formation ability dilemma of competitive learning. This algorithm is based on growing cell structures of self-organizing mapping. The new algorithm is effective for endless learning and automatic classification. Applying the algorithm in the case where the input pattern is changed temporally, we have confirmed that it has much better performance than conventional algorithms
Keywords :
cellular neural nets; pattern classification; self-organising feature maps; unsupervised learning; adaptive self organizing network; automatic classification; competitive learning; endless learning; formation ability; growing cell structures; input pattern; self-organizing mapping; stability; Adaptive systems; Automatic control; Cellular neural networks; Classification algorithms; Counting circuits; Frequency; Iron; Probability distribution; Self-organizing networks; Stability;
Conference_Titel :
Cellular Neural Networks and their Applications, 1996. CNNA-96. Proceedings., 1996 Fourth IEEE International Workshop on
Conference_Location :
Seville
Print_ISBN :
0-7803-3261-X
DOI :
10.1109/CNNA.1996.566487
