Drexel dragonThe Math ForumDonate to the Math Forum



Search All of the Math Forum:

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


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

Topic: neural network
Replies: 2   Last Post: Jan 24, 2013 7:44 PM

Advanced Search

Back to Topic List Back to Topic List Jump to Tree View Jump to Tree View  
Greg Heath

Posts: 5,871
Registered: 12/7/04
Re: neural network
Posted: Jan 24, 2013 7:44 PM
  Click to see the message monospaced in plain text Plain Text   Click to reply to this topic Reply

"Jamaa Ambarak" <jamaa73@yahoo.com> wrote in message <kdpi8b$fhi$1@newscl01ah.mathworks.com>...
> "Jamaa Ambarak" <jamaa73@yahoo.com> wrote in message <kdphjo$ctq$1@newscl01ah.mathworks.com>...
> > "Greg Heath" <heath@alumni.brown.edu> wrote in message <kdgo47$lcd$1@newscl01ah.mathworks.com>...
> > > "Greg Heath" <heath@alumni.brown.edu> wrote in message <kdfl30$t82$1@newscl01ah.mathworks.com>...
> > >
> > > ---SNIP
> > >

> > > > [ net, tr, Y, E ] = train(net,pn,T); % Yn = sim(net,pn); E = T-Yn
> > >
> > > Correction: If you do not normalize T, remove the subscript "n" from Y.
> > >
> > > Greg

> > please Greg tell me
> > first I have tried to train the neural without normalize but the results are very bad because the data should be normalize (speed velocity is 20-80 mile per hours and the other big also ). I did not normalize T , but how can I convert y back to the original scale using
> > y1 =mapminmax('reverse',y,ts);


Just use whatever is in the documentation.

help mapminmax

doc mapminmax

> also how can I validate the training and testing

See comp.ai.neural-nets for the NN concepts of validation and testing.

data = design + test
design = train + validate

Training set estimates weights

Validation set is used repeatedly with the training set to determine all other learning parameters (especially the stopping epoch), and to choose the best out of multiple designs.

Test set is used on 'best' design to obtain an unbiased estimate of performance on nondesign data.

If the test set performance is unsatisfactory, the data must be divided again before
designing new candidates.

Hope this helps.

Greg



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

[Privacy Policy] [Terms of Use]

© Drexel University 1994-2014. All Rights Reserved.
The Math Forum is a research and educational enterprise of the Drexel University School of Education.