how to make a neural network with a large matrix as inputs?

this is the code:

Ptr=xlsread('liaa(16s).xlsx','sheet1','I3:I402');

T=xlsread('liaa(16s).xlsx','sheet1','G3:G402');

net=newff(Ptr,T,4,{'logsig','purelin'},'trainlm','learngdm');

[net,tr]=train(net,Ptr,T);

y=sim(net,Ptr)
plot(Ptr,T,'bo',Ptr,y,'r*');
title('Perbandingan antara Target (o) dan Output Jaringan (*)');
xlabel('input');

and the errors said:

??? Error using ==> plus
Matrix dimensions must agree.

Error in ==> calcperf2 at 163
        N{i,ts} = N{i,ts} + Z{k};

Error in ==> trainlm at 253
[perf,El,trainV.Y,Ac,N,Zb,Zi,Zl] = calcperf2(net,X,trainV.Pd,trainV.Tl,trainV.Ai,Q,TS);

Error in ==> network.train at 219
  [net,tr] = feval(net.trainFcn,net,tr,trainV,valV,testV);

Error in ==> training_lia_vt at 11
[net,tr]=train(net,Ptr,T);

Both Ptr and T are 400x1 matrix, and i couldn't get the program to run unless the matrix get transposed. but if transpose the matrix the results i get is reversed. i'm supposed to get a graphic like this one:

but instead the result is:

Answer 1

[Greg Heath]

1. The matrices should be transposed.

2. there are 5 relevant plots

   a. input vs time
   b. target vs time
   c. target vs input
   d. output superimposed on b
   e. output superimposed on c

Hope this helps.

Thank you for formally accepting my answer

Greg

[Amalia]

Nah but if the matrices get transposed the output is reversed too. The graphic isn't formed right

[Greg Heath]

1x400 is correct. If your results are backwards use fliplr.

You can plot your results any way you want.

Greg