TY - GEN
T1 - A new multilayer feedforward small-world neural network with its performances on function approximation
AU - Li, Xiaohu
AU - Li, Xiaoling
AU - Zhang, Jinhua
AU - Zhang, Yulin
AU - Li, Maolin
PY - 2011
Y1 - 2011
N2 - In this paper, by the use of the research results from complex network, a new multilayer feedforward small-world neural network is presented. Firstly, based on the construction ideology of Watts-Strogatz network model and community structure, a new multilayer feedforward small-world neural network is built up, which heavily relies on the rewiring probability. Secondly, the network model is briefly described by mathematical method. Finally, in order to investigate the performances of new small-world neural network, function approximation and fault tolerance are used to test the network performances. Simulation results show that the new neural network has the best approximate performance when the rewiring probability is nearby 0.1, and the approximate speed comparison also shows that small-world neural network is superior to regular network and random network at this time.
AB - In this paper, by the use of the research results from complex network, a new multilayer feedforward small-world neural network is presented. Firstly, based on the construction ideology of Watts-Strogatz network model and community structure, a new multilayer feedforward small-world neural network is built up, which heavily relies on the rewiring probability. Secondly, the network model is briefly described by mathematical method. Finally, in order to investigate the performances of new small-world neural network, function approximation and fault tolerance are used to test the network performances. Simulation results show that the new neural network has the best approximate performance when the rewiring probability is nearby 0.1, and the approximate speed comparison also shows that small-world neural network is superior to regular network and random network at this time.
KW - artificial neural network
KW - complex network
KW - small-world network
UR - https://www.scopus.com/pages/publications/80051861619
U2 - 10.1109/CSAE.2011.5952696
DO - 10.1109/CSAE.2011.5952696
M3 - 会议稿件
AN - SCOPUS:80051861619
SN - 9781424487257
T3 - Proceedings - 2011 IEEE International Conference on Computer Science and Automation Engineering, CSAE 2011
SP - 353
EP - 357
BT - Proceedings - 2011 IEEE International Conference on Computer Science and Automation Engineering, CSAE 2011
T2 - 2011 IEEE International Conference on Computer Science and Automation Engineering, CSAE 2011
Y2 - 10 June 2011 through 12 June 2011
ER -