کمک

[azadmnesh]

newff


Create feedforward backpropagation network

Syntax

net = newff(PR,[S1 S2...SNl],{TF1 TF2...TFNl},BTF,BLF,PF)



Description


newff(PR,[S1 S2...SNl],{TF1 TF2...TFNl},BTF,BLF,PF) takes several arguments

PRR x 2 matrix of min and max values for R input elementsSiSize of ith layer, for Nl layersTFiTransfer function of ith layer (default = 'tansig&#039BTFBackpropagation network training function (default = 'traingdx&#039BLFBackpropagation weight/bias learning function (default = 'learngdm&#039PFPerformance function (default = 'mse&#039


Examples


Here is a problem consisting of inputs P and targets T to be solved with a network.
P = [0 1 2 3 4 5 6 7 8 9 10];((الگو های آموزش
T = [0 1 2 3 4 3 2 1 2 3 4];(اهداف آموزش)



A two-layer feedforward network is created. The network's input ranges from [0 to 10]. The first layer has five tansig neurons, and the second layer has one purelin neuron. The trainlm network training function is to be used.
net = newff([0 10],[5 1],{'tansig' 'purelin'});
توضیح د ستور:
)[min max of pattern),(number ofhiden layer neuron number of output),(transfer function of hiden layer transfer function of output layer)]



The network is simulated and its output plotted against the targets.
شبیه سازی یک الگو در الکوهای آموزش یا تست:
Y = sim(net,P);
plot(P,T,P,Y,'o&#039



The network is trained for 50 epochs. Again the network's output is plotted.
net.trainParam.epochs = 50;(تکرار الگوریتم)
net = train(net,P,T);
Y = sim(net,P);
plot(P,T,P,Y,'o&#039

کسی می تونه این کدو واسه ی من توضیح بده من نمی فهممش لطفا منتظر توضیحات شما هستم