On the Structure of Multilayer Cellular Neural Networks: Complexity between Two Layers
Jung-Chao Ban*
Department of Applied Mathematics, National Dong Hwa University
Hualian 97401, Taiwan, ROC
Chih-Hung Chang†
Department of Applied Mathematics, National University of Kaohsiung
Kaohsiung 81148, Taiwan, ROC
*jcban@mail.ndhu.edu.tw
†Corresponding author: chchang@nuk.edu.tw
Abstract
Let 
be the solution space of an n-layer cellular neural network, and let 
and 
be the hidden spaces, where 
, 
. (
is called the output space.) The classification and the existence of factor maps between two hidden spaces that reach the same topological entropies are investigated in [1]. This paper elucidates the existence of factor maps between those hidden spaces carrying distinct topological entropies. For either case, the Hausdorff dimensions 
and 
can be calculated. Furthermore, the dimensions of and ) are related by the factor map between them.
