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: Training multiple data for a single feedforwardnet
Replies: 19   Last Post: Dec 1, 2012 6:14 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: 5,947
Registered: 12/7/04
Re: Training multiple data for a single feedforwardnet
Posted: Oct 20, 2012 6:41 PM
  Click to see the message monospaced in plain text Plain Text   Click to reply to this topic Reply

"Carlos Aragon" wrote in message <k5n37h$ier$1@newscl01ah.mathworks.com>...
> I'm building a feedforwardnet like this:
>
> (..)
> P=[V';ia';w'];
> T=[tq'];
> net=feedforwardnet([5 25],'trainbr');
> (..)
>
> How could i train this neural net for more then one group '[V';ia';w']' ? How is the matlab structure to perform this kind of training?
>
> Note that 'P' in this case is a 10006x3 matrix that i extract from a motor model.


The issue here is that after training with set1, the weights will forget set1
while they are learning set 2. There are a variety of ways to mitigate forgetting.

The best is to use a modication of NEWRB that allows the input of an initial
hidden layer. Then

1. After training with set1, use those weights as initial weights for training with set2 + set1.

2. After training with set1, use those weights as initial weights for training with set2 and a "characteristic subset" of set1. The drawback is how to define that characteristic.

The reason this works is that each hidden node basis function has local region of influence and a 1-to-1 correspondence with a previous worst classified training vector.

Hope this helps.

Greg


Date Subject Author
10/17/12
Read Training multiple data for a single feedforwardnet
Carlos Aragon
10/19/12
Read Re: Training multiple data for a single feedforwardnet
Greg Heath
10/20/12
Read Re: Training multiple data for a single feedforwardnet
Greg Heath
10/29/12
Read Re: Training multiple data for a single feedforwardnet
Carlos Aragon
10/31/12
Read Re: Training multiple data for a single feedforwardnet
Greg Heath
11/1/12
Read Re: Training multiple data for a single feedforwardnet
Carlos Aragon
11/1/12
Read Re: Training multiple data for a single feedforwardnet
Greg Heath
11/3/12
Read Re: Training multiple data for a single feedforwardnet
Carlos Aragon
11/3/12
Read Re: Training multiple data for a single feedforwardnet
Greg Heath
11/5/12
Read Re: Training multiple data for a single feedforwardnet
Carlos Aragon
11/16/12
Read Re: Training multiple data for a single feedforwardnet
Carlos Aragon
11/17/12
Read Re: Training multiple data for a single feedforwardnet
Greg Heath
11/17/12
Read Re: Training multiple data for a single feedforwardnet
Carlos Aragon
11/17/12
Read Re: Training multiple data for a single feedforwardnet
Greg Heath
11/17/12
Read Re: Training multiple data for a single feedforwardnet
Carlos Aragon
11/17/12
Read Re: Training multiple data for a single feedforwardnet
Greg Heath
11/18/12
Read Re: Training multiple data for a single feedforwardnet
Carlos Aragon
11/18/12
Read Re: Training multiple data for a single feedforwardnet
Greg Heath
12/1/12
Read Re: Training multiple data for a single feedforwardnet
Carlos Aragon
10/29/12
Read Re: Training multiple data for a single feedforwardnet
Carlos Aragon

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.