Why does [ I N ] & [ O N ] for the neural network doesn't work??

1 view (last 30 days)
Hi,
I'm using MATLAB R2015a. I have the input data, data (1100x90) and target, t (2x90).
I'm not sure how to set the target but I've found the way to set the target by referring from this page;
Am I doing the right approach in setting the target?
Here is how I'm setting the input and target for neural network;
data = horzcat( data{:} ) ; % data 1100x90 double
% target setting
t = zeros (2, 90);
t (1, 1:45) = ones (1,45);
t (2, 46:90) = ones (1, 45); % t 2x90 double
% neural network setting
[ I N ] = [1100 90]
[ O N ] = [2 90]
net = patternnet(10);
[net,tr] = train(net,data,t);
I've only reached here and I got this error.
Too many output arguments.
Error in test_nn (line 24)
[ I N ] = [1100 90]
Please help me to resolve this error.
Thank you
Hana

Accepted Answer

Greg Heath
Greg Heath on 9 Nov 2017
% I don't know why, but that method of multiple variable assignment is only defined for functions
>> x = 0, y = 0
x = 0
y = 0
>> [ x y ] = [ 1 2 ]
Too many output arguments.
>> [ x y ] = [ 1, 2 ]
Too many output arguments.
>> [ x, y ] = [ 1, 2 ]
Too many output arguments.
>> [ x, y ] = [ 1 2 ]
Too many output arguments.
Hope this helps.
Thank you for formally accepting my answer
Greg
  3 Comments
Greg Heath
Greg Heath on 11 Nov 2017
EDITED QUESTIONS:
Q1. This is my first project using MATLAB. Will you please explain, in detail, why "multiple variable assignments" are only defined for functions'?
A. I don't know.
Q2. Also, I don't really get what this code means.
A. It just means that your syntax is incorrect.
Q3. What should I do to avoid from getting the same error?
A. Don't use that syntax. I have demonstrated 4 versions and they are all unacceptable.
Use the versions I use in my codes.
Hope this helps.
Greg
hana razak
hana razak on 12 Nov 2017
Thank you very much for your answers. You really help me a lot.

Sign in to comment.

More Answers (0)

Categories

Find more on Sequence and Numeric Feature Data Workflows in Help Center and File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!