Hallo,
Can anyone explain why 'sim' command in neural network is not working in Matlab version 2015 and above? After training the network, I wanted to simulate the values to predict the accuracy of the network. I used the command :
y=sim(net,p); where y is the simulated values matrix of the input matrix p
When i try to do the same using the neural network toolbox, I was able to simulate the values but not able to use 'sim' as objective function for the subsequent optimization methods.
Regards, Bharath

 Réponse acceptée

Greg Heath
Greg Heath le 13 Mar 2016

1 vote

Replace
train( net, p, t )
with reasonable variations of
[ net tr y e ] = train( net, p, t );
where y = net( x ) and e = t-y
Hope this helps.
Thank you for formally accepting my answer

Plus de réponses (2)

Greg Heath
Greg Heath le 11 Mar 2016

0 votes

You cannot use the names of MATLAB commands or functions for your own use. They are RESERVED.
Any of the commands
lookfor sim
help sim
doc sim
which sim
would have indicated a reserved name.
By the way, as you can gather from the help or doc documentation on fitnet, patternnet, etc the command y = sim(net,x) has been replaced by y = net(x). SIM is now used w.r.t. SIMULINK.
Hope this helps.
Thank you for formally accepting my answer
Greg
Bharathwaj Krishnamoorthi
Bharathwaj Krishnamoorthi le 11 Mar 2016
Modifié(e) : Bharathwaj Krishnamoorthi le 11 Mar 2016

0 votes

Hi Greg,
I appreciate your answer. And I was not using the Matlab commands for my own use. Please check the command for simulating the neural network in pre-Matlab2015 versions. I have attached the picture containing the result ( which is an empty matrix) when i used both sim(net,x) and net(x).
Looking for an answer,
Bharath

2 commentaires

Steven Lord
Steven Lord le 11 Mar 2016
Type this command at the Trial>> prompt and show the output.
net
Greg Heath
Greg Heath le 11 Mar 2016
Modifié(e) : Walter Roberson le 14 Mar 2016
Your attachment is unreadable. Just cut and paste the code. Greg
NEVER MIND: CTRL + DID THE JOB!

Connectez-vous pour commenter.

Catégories

En savoir plus sur Deep Learning Toolbox dans Centre d'aide et File Exchange

Community Treasure Hunt

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

Start Hunting!

Translated by