The authors discuss problems of approximation to functions in L2(Rn) and operators fromL2(Rn1) to L2(Rn2) by Radial-Basis Functions. The results obtained solve the problem ofcapability of RBF neural networks, a basic ...The authors discuss problems of approximation to functions in L2(Rn) and operators fromL2(Rn1) to L2(Rn2) by Radial-Basis Functions. The results obtained solve the problem ofcapability of RBF neural networks, a basic problem in neural networks.展开更多
Recently many researches suggest that CEO compensation is not only related to performance. And this relation is non-linear. This paper analyzes CEO compensation, salary and stockholding value with BP neutral network w...Recently many researches suggest that CEO compensation is not only related to performance. And this relation is non-linear. This paper analyzes CEO compensation, salary and stockholding value with BP neutral network with the data from listed companies during 2003--2005 in China. The results are： 1） The fitness of network outputs are 91.09%, 97：23% and 78.44% respectively; 2） The accurate of forecast improves 92.72%, 92.08% and 53.89% respectively comparing with the results of multi-regression model.展开更多
基金Project supported by the National Natural Science Foundation of Chin
文摘The authors discuss problems of approximation to functions in L2(Rn) and operators fromL2(Rn1) to L2(Rn2) by Radial-Basis Functions. The results obtained solve the problem ofcapability of RBF neural networks, a basic problem in neural networks.
基金This project is supported by National Natural Science Foundation of China （70671058）
文摘Recently many researches suggest that CEO compensation is not only related to performance. And this relation is non-linear. This paper analyzes CEO compensation, salary and stockholding value with BP neutral network with the data from listed companies during 2003--2005 in China. The results are： 1） The fitness of network outputs are 91.09%, 97：23% and 78.44% respectively; 2） The accurate of forecast improves 92.72%, 92.08% and 53.89% respectively comparing with the results of multi-regression model.
