生成一组带有高斯噪声的样本,分别用一阶,二阶,三阶的最小二乘估计方法进行拟合,然后分别用AIC,MDL,FPE,CAT四种评测模型对其性能进行比较,得到最优的拟合模型.
上传时间: 2016-05-08
上传用户:shawvi
在系统辨识过程中,系统介数未知,估计模型阶次的FPE法
上传时间: 2014-12-05
上传用户:skhlm
按FPE定阶的 源程序:FPE.cpp M序列:M序列.txt 白噪声:Gauss.txt 程序中先用依模型阶次递推算法估计模型的参数,再用FPE方法判断模型的阶次。 程序运行结果如下: n: 1 判断阶次FPE的值: 0.0096406 -0.481665 1.07868 n: 2 判断阶次FPE的值: 0.00875755 -0.446739 0.00498181 1.07791 0.0527289 n: 3 判断阶次FPE的值: 0.0087098 -0.459433 0.120972 -0.0569228 1.07814 0.0390757 0.116982 n: 4 判断阶次FPE的值: 0.000396884 -0.509677 0.4501 -0.200906 0.0656188 1.07991 -0.0156362 0.442989 0.0497236 n: 5 判断阶次FPE的值: 3.2095e-007 -1.18415 0.813123 -0.517862 0.34881 -0.116864 1.07999 -0.744141 0.474462 -0.253112 0.122771 n: 6 判断阶次FPE的值: 3.23349e-007 -1.14659 0.76933 -0.487651 0.329676 -0.10377 -0.00440907 1.07999 -0.703574 0.447253 -0.235282 0.113587 0.00479688 从以上结果可以看出,当n=5时,FPE值最小,所以这时的模型阶次和参数估计值为最优结果: 3.2095e-007 -1.18415 0.813123 -0.517862 0.34881 -0.116864 1.07999 -0.744141 0.474462 -0.253112 0.122771
上传时间: 2013-12-11
上传用户:yd19890720
This function calculates Akaike s final prediction error % estimate of the average generalization error. % % [FPE,deff,varest,H] = FPE(NetDef,W1,W2,PHI,Y,trparms) produces the % final prediction error estimate (FPE), the effective number of % weights in the network if the network has been trained with % weight decay, an estimate of the noise variance, and the Gauss-Newton % Hessian. %
标签: generalization calculates prediction function
上传时间: 2014-12-03
上传用户:maizezhen
This function calculates Akaike s final prediction error % estimate of the average generalization error for network % models generated by NNARX, NNOE, NNARMAX1+2, or their recursive % counterparts. % % [FPE,deff,varest,H] = nnFPE(method,NetDef,W1,W2,U,Y,NN,trparms,skip,Chat) % produces the final prediction error estimate (FPE), the effective number % of weights in the network if it has been trained with weight decay, % an estimate of the noise variance, and the Gauss-Newton Hessian. %
标签: generalization calculates prediction function
上传时间: 2016-12-27
上传用户:脚趾头
本教程包含了(WPE,FPE)编程类(动作式,单机游戏改式,盗号工具制作,加速式外挂,网络游戏数据修改),还有丰富源码。-
上传时间: 2013-12-24
上传用户:徐孺
程序中先用依模型阶次递推算法估计模型的参数,再用FPE方法判断模型的阶次。
上传时间: 2017-08-13
上传用户:qb1993225