Solved

In Neural Network training, how to represent instances that do not belong to any class

Posted on 2012-03-18
4
356 Views
Last Modified: 2013-11-25
Also, how should that be reflected into the design of the network itself?
I mean if the output of 0001 means 1 and the output of 0010 means 2, can we train the network to produce 0000 for instances that do not belong to any class?
0
Comment
Question by:Lamiaaa
[X]
Welcome to Experts Exchange

Add your voice to the tech community where 5M+ people just like you are talking about what matters.

  • Help others & share knowledge
  • Earn cash & points
  • Learn & ask questions
  • 2
4 Comments
 
LVL 31

Expert Comment

by:GwynforWeb
ID: 37735729
Are you using a forward-feeding (ie layers proceeding left-right) or a feedback network?
0
 
LVL 36

Assisted Solution

by:mccarl
mccarl earned 500 total points
ID: 37735762
Theoretically, yes, 0000 would mean no class, but in practical terms, you would have to evaluate the performance of that. It would depend on all the usual things with NN's, such as the input data, number of layers, number of neurons, how you train it, etc.
0
 

Author Comment

by:Lamiaaa
ID: 37735810
Thanks guys,

yes, it is forward-feeding.

Are there any sampling approaches (proposed to solve similar problems) to build a training set that appropriately represent the 0000 cases?

It seems difficult because "every thing else" is a very huge and diverse set!
0
 
LVL 36

Accepted Solution

by:
mccarl earned 500 total points
ID: 37735880
It is a bit hard to say, as only you know your problem domain. One possibility might be a random sample that is the same size as the total of all 'classified' samples, ie. of the total training set, half is "everything else' and the other half is 'one of the target classes'.

I would base this on the performance of the network as it stands. So first, you would include these 'everything else' inputs into your verification set, and see how the network performs. Then depending on the results of the verification step, modify the training set to see what improvements can be gained.
0

Featured Post

Independent Software Vendors: We Want Your Opinion

We value your feedback.

Take our survey and automatically be enter to win anyone of the following:
Yeti Cooler, Amazon eGift Card, and Movie eGift Card!

Question has a verified solution.

If you are experiencing a similar issue, please ask a related question

This article will show, step by step, how to integrate R code into a R Sweave document
When there is a disconnect between the intentions of their creator and the recipient, when algorithms go awry, they can have disastrous consequences.
Viewers will learn how to properly install Eclipse with the necessary JDK, and will take a look at an introductory Java program. Download Eclipse installation zip file: Extract files from zip file: Download and install JDK 8: Open Eclipse and …
Finds all prime numbers in a range requested and places them in a public primes() array. I've demostrated a template size of 30 (2 * 3 * 5) but larger templates can be built such 210  (2 * 3 * 5 * 7) or 2310  (2 * 3 * 5 * 7 * 11). The larger templa…

615 members asked questions and received personalized solutions in the past 7 days.

Join the community of 500,000 technology professionals and ask your questions.

Join & Ask a Question