Skip to Main Content Skip to Search
Login
File Exchange
MATLAB Newsgroup
Link Exchange
  Blogs  
 Contest 
MathWorks.com

Thread Subject: problem with train command function

Subject: problem with train command function

From: Manos

Date: 21 Jul, 2008 20:18:03

Message: 1 of 4

Hi all,

I tried to use the command function of train. Reading the
Neural Network Toolbox™ 6 User’s Guide, on page 1-26 and
1-27 it refered that after running train function Matlabs
automatically opens neural network training. When i tried
train function I did not get that. Is there any problem or
special adjustment that I have to do?

Thank you in advance,

Manolis

Subject: problem with train command function

From: Greg Heath

Date: 22 Jul, 2008 00:46:31

Message: 2 of 4

On Jul 21, 4:18=A0pm, "Manos " <ezoul...@in.gr> wrote:
> Hi all,
>
> I tried to use the command function of train. Reading the
> Neural Network Toolbox™ 6 User’s Guide, on page 1-26 and
> 1-27 it refered that after running train function Matlabs
> automatically opens neural network training. When i tried
> train function I did not get that. Is there any problem or
> special adjustment that I have to do?

Tou have to create the net with newff or new?? before using
train. if this doesnot solve your problem, please post your
relevant code.

Hope this helps.

Greg

Subject: problem with train command function

From: Manos

Date: 22 Jul, 2008 15:13:03

Message: 3 of 4

Dear Greg,

I load the sample data housing

load housing

I do create the net with

net = newff(p,t,100)

and then I train the net

net = train(net,p,t);
TRAINLM-calcjx, Epoch 0/100, MSE 6579.73/0, Gradient
26421.3/1e-010
TRAINLM-calcjx, Epoch 10/100, MSE 0.0381886/0, Gradient
24.8268/1e-010
TRAINLM, Validation stop.

My version is R7.5.0 (R2007b)

Thank you in advance,

Manolis
Greg Heath <heath@alumni.brown.edu> wrote in message
<36eece46-7145-4186-93bf-21fbb00484cc@m36g2000hse.googlegroups.com>...
> On Jul 21, 4:18=A0pm, "Manos " <ezoul...@in.gr> wrote:
> > Hi all,
> >
> > I tried to use the command function of train. Reading the
> > Neural Network Toolbox™ 6 User’s Guide, on page 1-26 and
> > 1-27 it refered that after running train function Matlabs
> > automatically opens neural network training. When i tried
> > train function I did not get that. Is there any problem or
> > special adjustment that I have to do?
>
> Tou have to create the net with newff or new?? before using
> train. if this doesnot solve your problem, please post your
> relevant code.
>
> Hope this helps.
>
> Greg

Subject: problem with train command function

From: Steven Lord

Date: 22 Jul, 2008 15:36:52

Message: 4 of 4


"Manos " <ezoulias@in.gr> wrote in message
news:g64tdv$fl8$1@fred.mathworks.com...
> Dear Greg,
>
> I load the sample data housing
>
> load housing
>
> I do create the net with
>
> net = newff(p,t,100)
>
> and then I train the net
>
> net = train(net,p,t);
> TRAINLM-calcjx, Epoch 0/100, MSE 6579.73/0, Gradient
> 26421.3/1e-010
> TRAINLM-calcjx, Epoch 10/100, MSE 0.0381886/0, Gradient
> 24.8268/1e-010
> TRAINLM, Validation stop.
>
> My version is R7.5.0 (R2007b)

It sounds like you're trying to use an older version of the Toolbox with the
documentation for the newest version, Neural Network Toolbox 6.0 (R2008a).
The nntraintool GUI to which I believe you're referring was introduced in
this version of the toolbox, as mentioned in the release notes for this
version.

http://www.mathworks.com/access/helpdesk/help/toolbox/nnet/rn/rn2.html#87460

It is not available in previous versions of the toolbox.

--
Steve Lord
slord@mathworks.com


Tags for this Thread

Add a New Tag:

Separated by commas
Ex.: root locus, bode

What are tags?

A tag is like a keyword or category label associated with each thread. Tags make it easier for you to find threads of interest.

Anyone can tag a thread. Tags are public and visible to everyone.

rssFeed for this Thread

envelope graphic E-mail this page to a colleague

Public Submission Policy
NOTICE: Any content you submit to MATLAB Central, including personal information, is not subject to the protections which may be afforded information collected under other sections of The MathWorks, Inc. Web site. You are entirely responsible for all content that you upload, post, e-mail, transmit or otherwise make available via MATLAB Central. The MathWorks does not control the content posted by visitors to MATLAB Central and, does not guarantee the accuracy, integrity, or quality of such content. Under no circumstances will The MathWorks be liable in any way for any content not authored by The MathWorks, or any loss or damage of any kind incurred as a result of the use of any content posted, e-mailed, transmitted or otherwise made available via MATLAB Central. Read the complete Disclaimer prior to use.
Related Topics