The Math Forum

Search All of the Math Forum:

Views expressed in these public forums are not endorsed by NCTM or The Math Forum.

Math Forum » Discussions » Software » comp.soft-sys.matlab

Notice: We are no longer accepting new posts, but the forums will continue to be readable.

Topic: Specify/change the error used by train command
Replies: 4   Last Post: Feb 4, 2013 2:15 PM

Advanced Search

Back to Topic List Back to Topic List Jump to Tree View Jump to Tree View   Messages: [ Previous | Next ]
Greg Heath

Posts: 6,387
Registered: 12/7/04
Re: Specify/change the error used by train command
Posted: Feb 4, 2013 2:16 AM
  Click to see the message monospaced in plain text Plain Text   Click to reply to this topic Reply

"AM76" wrote in message <ken93s$bs9$>...
> Hello
> I am in a work to use the neural network in a specific form that the output of the NN is multiplied by a system (Like G) and want to make output of G tracks a desired target. Therefore, the error between target and G should be used to train the NN so I can't use train (as far as I know) command directly because the NN train the net from the error between the target and the direct NN output. I was wondering how to use train command in such a system?
> Note. This system is used in model reference control in Simulink/Neural network, but I don't use Simulink.

I don't understand.

Please explain "output of the NN is multiplied by a system"

If you know what the output of the system should be for a given NN input, why
don't you just train the net to yield that desired output?

Hope this helps.


Point your RSS reader here for a feed of the latest messages in this topic.

[Privacy Policy] [Terms of Use]

© The Math Forum at NCTM 1994-2018. All Rights Reserved.