TY - GEN
T1 - Variable thresholds in the chaotic cellular neural network
AU - Liu, Wen
AU - Wang, Lipo
PY - 2007
Y1 - 2007
N2 - The chaotic cellular neural network (C-CNN) has complex dynamics, including chaos, oscillations, and stable fixed points. Chaotic dynamics can help the network avoid local minima and reach the global optimum. Hence chaos can improve the performance of cellular neural networks (CNNs) on problems that have local minima in energy (cost) functions. We investigate the effect of variable thresholds in the C-CNN. We show that this threshold cannot be too large if one wishes to produce chaotic dynamics in the C-CNN, which is important to studies of chaotic communication and combinatorial optimization problem. We are particularly interested in variable thresholds because Shi and Wang [1] showed that the objectives of the frequency assignment problem (FAP) can be mapped into thresholds of the neural network, which resulted in superior performance compared to traditional penalty approaches.
AB - The chaotic cellular neural network (C-CNN) has complex dynamics, including chaos, oscillations, and stable fixed points. Chaotic dynamics can help the network avoid local minima and reach the global optimum. Hence chaos can improve the performance of cellular neural networks (CNNs) on problems that have local minima in energy (cost) functions. We investigate the effect of variable thresholds in the C-CNN. We show that this threshold cannot be too large if one wishes to produce chaotic dynamics in the C-CNN, which is important to studies of chaotic communication and combinatorial optimization problem. We are particularly interested in variable thresholds because Shi and Wang [1] showed that the objectives of the frequency assignment problem (FAP) can be mapped into thresholds of the neural network, which resulted in superior performance compared to traditional penalty approaches.
UR - http://www.scopus.com/inward/record.url?scp=51749121246&partnerID=8YFLogxK
U2 - 10.1109/IJCNN.2007.4371044
DO - 10.1109/IJCNN.2007.4371044
M3 - Conference Proceeding
AN - SCOPUS:51749121246
SN - 142441380X
SN - 9781424413805
T3 - IEEE International Conference on Neural Networks - Conference Proceedings
SP - 711
EP - 714
BT - The 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings
T2 - 2007 International Joint Conference on Neural Networks, IJCNN 2007
Y2 - 12 August 2007 through 17 August 2007
ER -