TY - GEN
T1 - Spatial complexity in multi-layer cellular neural networks
AU - Ban, Jung Chao
AU - Chang, Chih Hung
AU - Lin, Song-Sun
AU - Lin, Yin Heng
PY - 2010/5/21
Y1 - 2010/5/21
N2 - This study investigates the complexity of the global set of output patterns for one-dimensional multi-layer cellular neural networks with input. Applying labeling to the output space produces a sofic shift space. Two invariants, namely spatial entropy and dynamical zeta function, can be exactly computed by studying the induced sofic shift space. This study gives sofic shift a realization through a realistic model. Furthermore, a new phenomenon, the broken of symmetry of entropy, is discovered in multi-layer cellular neural networks with input.
AB - This study investigates the complexity of the global set of output patterns for one-dimensional multi-layer cellular neural networks with input. Applying labeling to the output space produces a sofic shift space. Two invariants, namely spatial entropy and dynamical zeta function, can be exactly computed by studying the induced sofic shift space. This study gives sofic shift a realization through a realistic model. Furthermore, a new phenomenon, the broken of symmetry of entropy, is discovered in multi-layer cellular neural networks with input.
UR - http://www.scopus.com/inward/record.url?scp=77952387018&partnerID=8YFLogxK
U2 - 10.1109/CNNA.2010.5430257
DO - 10.1109/CNNA.2010.5430257
M3 - Conference contribution
AN - SCOPUS:77952387018
SN - 9781424466795
T3 - 2010 12th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2010
BT - 2010 12th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2010
T2 - 2010 12th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2010
Y2 - 3 February 2010 through 5 February 2010
ER -