Math Forum Discussions

Murugan Solaiyappan

Posts: 15
Registered: 12/4/10

how to train the network for stock data
Posted: Nov 27, 2012 11:58 PM

Plain Text

Dear matlab friends,
Greetings to all.

I have trouble with train the stock data.
here my code is,

load ti_out_t.data;
P=ti_out_t(1:189,1:12);
T=ti_out_t(1:189,13:24);
[pn,minp,maxp,tn,mint,maxt]=premnmx(P',T');
net=newff(minmax(pn),[24 1],{'tansig','tansig'},'traingdm');
net.trainParam.epochs=75;
net.trainParam.lr=0.3;
net.trainParam.mc=0.6;
net=train(net,pn,tn);

ti_out_t.data contains 271 rows and 24 columns.
P is input data and t is output data.

When I execute the above code in matlab, the following error displayed,

??? Error using ==> network.train at 145
Targets are incorrectly sized for network.
Matrix must have 1 rows.

Error in ==> nn_taiwan_12input at 9
net=train(net,pn,tn);

I can't understand the error,

Please any one of you help me my dear friends.