TY - GEN
T1 - Polynomial discrete time Cellular Neural Networks to solve the XOR problem
AU - Gomez-Ramirez, Eduardo
AU - Pazienza, Giovanni Egidio
AU - Vilasis-Cardona, Xavier
PY - 2006
Y1 - 2006
N2 - Some papers discuss different option to improve the capabilities of Cellular Neural Networks (CNN), The principal point is that a single layer CNN can not solve problems with linearly nonsepurable data. In this paper a new model called Polynomial Discrete Time Cellular Neural networks is presented. This model has a very simple nonlinear term that can improve the performance of the network. The results show how it is possible to solve the XOR problem. The templates of the entire network are computed using genetic algorithm,
AB - Some papers discuss different option to improve the capabilities of Cellular Neural Networks (CNN), The principal point is that a single layer CNN can not solve problems with linearly nonsepurable data. In this paper a new model called Polynomial Discrete Time Cellular Neural networks is presented. This model has a very simple nonlinear term that can improve the performance of the network. The results show how it is possible to solve the XOR problem. The templates of the entire network are computed using genetic algorithm,
KW - Genetic algorithm
KW - Polynomial discrete time Cellular Neural Networks
KW - XOR problem
UR - http://www.scopus.com/inward/record.url?scp=47549106867&partnerID=8YFLogxK
U2 - 10.1109/CNNA.2006.341598
DO - 10.1109/CNNA.2006.341598
M3 - Conference contribution
AN - SCOPUS:47549106867
SN - 1424406404
SN - 9781424406401
T3 - Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications
BT - Proceedings of the 2006 10th IEEE International Workshop on Cellular Neural Networks and their Applications, CNNA 2006
T2 - 2006 10th IEEE International Workshop on Cellular Neural Networks and their Applications, CNNA 2006
Y2 - 28 August 2006 through 30 August 2006
ER -