AForge.NET

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

Why is solution not exact when "fixed"

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

Why is solution not exact when "fixed"

Postby Lawrence » Tue May 24, 2016 8:27 am

FixedData.PNG
Solution and data - not the same
FixedData.PNG (137.23 KiB) Viewed 5402 times


Hi,

I am using

ActivationNetwork network = new ActivationNetwork(
new BipolarSigmoidFunction(sigmoidAlphaValue),
inputList.Count,
inputList.Count,
1);

BackPropagationLearning teacher = new BackPropagationLearning(network);

With the same data for input AND output - just to see process of weights being set.

So inputList.Count == 1;

Why does the solution line, not match the data line exactly. They are the same data...
Lawrence
 
Posts: 24
Joined: Tue May 17, 2016 11:32 am

Re: Why is solution not exact when "fixed"

Postby andrew.kirillov » Tue May 24, 2016 9:01 am

Hello,

Network's weights are set randomly initially. Then you teach it to get result you need. Obviously it may take certain number of iterations for weights to converge to "optimal". Play with number of iterations, learning parameters ...
With best regards,
Andrew


Interested in supporting AForge.NET Framework?
User avatar
andrew.kirillov
Site Admin, AForge.NET Developer
 
Posts: 3363
Joined: Fri Jan 23, 2009 9:12 am
Location: UK

Re: Why is solution not exact when "fixed"

Postby Lawrence » Tue May 24, 2016 10:02 am

Fixed2.PNG
Fixed2.PNG (124.22 KiB) Viewed 5399 times


Hi Andrew,

I have actually tried all manner of variants of the parameters but I still never get to an exact match - is that because of the Sigmoid?

I can't get better match than the picture above.
Lawrence
 
Posts: 24
Joined: Tue May 17, 2016 11:32 am




Return to Artificial Intelligence