MATLAB: What dose the “Index exceeds matrix dimensions” mean when I train a dynamic neuron networks

Question

I did the example follow the Neural Network Use's guide 2012b on page 1-35,After entering the code which are follow:

net = linearlayer([0 1],0.02);
net.inputs{1}.size = 1;
net.layers{1}.dimensions = 1;
net.IW{1,1} = [0 0];
net.biasConnect = 0;
net.trainParam.epochs = 1;
Pi = {1};
P = {2 3 4};
T = {3 5 6};
net = train(net,P,T,Pi);

I got the result:

Index exceeds matrix dimensions.
Error in trainb>train_network (line 206)
            [dw,IWLS{i,j}] = learnFcn.apply(net.IW{i,j}, ...
Error in trainb (line 55)
        [out1,out2] = train_network(varargin{2:end});
Error in network/train (line 274)
  [net,tr] = feval(net.trainFcn,'apply',net,tr,data,hints,net.trainParam);

Who can explain this situation for me ? Are the command codes on the user's guide book wrong? How can I fix the problem?

Answer 1

 close all, clear all, clc
 net = linearlayer([0 1],0.02);
 net.inputs{1}.size = 1;
 net.layers{1}.dimensions = 1;
 net.IW{1,1} = [0 0];
 net.biasConnect = 0;
% net.trainParam.epochs = 1;
 Pi = {1};
 P = {2 3 4};
 T = {3 5 6};
 for i=1:5
    net.IW{1,1} = [ randn/100 randn/100 ];
    net = train(net,P,T,Pi);
    y = net(P)
 end
y =     [3.2583]    [4.6624]    [6.1790]
y =     [3.2590]    [4.6624]    [6.1789]
y =     [3.2598]    [4.6625]    [6.1788]
y =     [3.2587]    [4.6624]    [6.1789]
y =     [3.2575]    [4.6623]    [6.1791]

Thank you for formally accepting my answer

Greg