Hierarchical growing cell structures
Vanco Burzevski, Chilukuri Krishna Mohan · 2002
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.