AForge.NET

  :: AForge.NET Framework :: Articles :: Forums ::

How to map the parameters with good and bad effect in input?

The forum is to discuss topics from different artificial intelligence areas, like neural networks, genetic algorithms, machine learning, etc.

How to map the parameters with good and bad effect in input?

Postby Edrisfm » Sun Jan 17, 2010 3:38 am

Hello
I use MLP for soccer prediction. There are some input properties. It seems that some of them have good effect on result(like: shoots on target count) and some of them have bad effect(like bad passes count).

Now, my question is in mapping data for input, I should map both of properties in a same approach(NN modifies weights correctly) or I should map data with negative approach(for example: 1's complement)
Edrisfm
 
Posts: 5
Joined: Mon Jan 04, 2010 5:04 am
Location: Iran - Kermanshah

Re: How to map the parameters with good and bad effect in input?

Postby andrew.kirillov » Mon Jan 18, 2010 11:19 am

Hello,

Hard to say for sure without learning the problem deeply. But why don't we let neural network to figure it out? As you've mentioned, during learning phase it will update its weights on its own.
With best regards,
Andrew


Interested in supporting AForge.NET Framework?
User avatar
andrew.kirillov
Site Admin, AForge.NET Developer
 
Posts: 3427
Joined: Fri Jan 23, 2009 9:12 am
Location: UK




Return to Artificial Intelligence