Neural network for multiple input and multi output (MIMO) systems
14 views (last 30 days)
Show older comments
I want to build a neural network for a multi input and multi output (MIMO) system described as:
y1(t)= f1( x1(t), x2(t),...xn(t))
y2(t)= f2( x1(t), x2(t),...xn(t))
.....
.....
ym(t)= fm( x1(t), x2(t),...xn(t))
For single input single output system, mostly for function approximation of the form `y= f(t)`, where the neural network is trained for input t (independent variable) and output y, there are many examples. However, how do I construct or solve the MIMO problem ? How to I transform or represent the input or outputs to solve the problem with the matlab neural network toolbox?
0 Comments
Accepted Answer
Greg Heath
on 25 Jan 2013
The typical NN is a MIMO function and the typical NNTBX design uses I-dimensional inputs
[ I N ] = size(input)
and O-dimensional output targets
[ O N ] = size(target)
Interpret all variables as rows of input and output matrices
Hope this helps.
Thank you for formally accepting my answer.
Greg
0 Comments
More Answers (1)
Shashank Prasanna
on 24 Jan 2013
create different networks for each fi. fi: x1..xn -> yi
Also can you provide a little context to the questions? What is this for and where will you be using it?
0 Comments
See Also
Categories
Find more on Sequence and Numeric Feature Data Workflows in Help Center and File Exchange
Products
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!