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: feed-forward back-propogation network
Replies: 1   Last Post: Apr 23, 2013 1:00 AM

Advanced Search

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

Posts: 5,965
Registered: 12/7/04
Re: feed-forward back-propogation network
Posted: Apr 23, 2013 1:00 AM
  Click to see the message monospaced in plain text Plain Text   Click to reply to this topic Reply

"saad elazzouzi" wrote in message <kl3mf1$ive$1@newscl01ah.mathworks.com>...
> hi,
> I am trying to create a feed-forward back-propogation network with
> 3 inputs vetcors, 2 hidden layer with 7 nodes, and 2 output vectors .


Incorrect. You have

50 3-dimensional input vectors.
50 2-dimensional target vectors
1 hidden layer with 7 nodes
1 output layer with 2 nodes
1 fan-in unit input with 3 nodes (I do not like this notation either)

> P=vibrationdata(1:50,1:2:3);

Incorrect.
>> 1:2:3
ans = 1 3

> net=newff(minmax(pn),[7 1],{'tansig','tansig'},'traingdm')

Incorrect

net=newff( minmax(pn), [ 7 2 ], {'tansig','tansig'}, 'traingdm' ); % note "2" and semicolon

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.