Title :
Hierarchical growing cell structures
Author :
Burzevski, Vanco ; Mohan, Chilukuri K.
Author_Institution :
Sch. of Comput. & Inf. Sci., Syracuse Univ., NY, USA
Abstract :
We propose a hierarchical self-organizing neural network with adaptive architecture and simple topological organization. This network combines features of Fritzke´s growing cell structures and traditional hierarchical clustering algorithms. The height and width of the tree structure depend on the user-specified level of error desired, and the weights in upper layers of the network do not change in later phases of the learning algorithm
Keywords :
adaptive systems; learning (artificial intelligence); network topology; neural net architecture; self-organising feature maps; trees (mathematics); adaptive architecture; hierarchical clustering; hierarchical growing cell structures; learning algorithm; self-organizing neural network; topological organization; tree structure; Adaptive systems; Clustering algorithms; Computational Intelligence Society; Frequency; Learning systems; Network topology; Neural networks; Plastics; Stability; Tree data structures;
Conference_Titel :
Neural Networks, 1996., IEEE International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-3210-5
DOI :
10.1109/ICNN.1996.549149
