Dave Harris wrote:
> Dave Harris wrote:
>   
>> Mitchell Timin wrote:
>>     
>>> Biggerun.bat found a perfect 4-neuron ANN for the 3 step path; it is
>>> attached.  It was evolved for 3 and 4 steps, hence the name.
>>>       
>> <Pettiness alert>
>> I thought the convention was "minSteps-maxSteps-NeuronCount-Fitness.sc". 
>> The
>> file should have been named 3-4s-4-perf.sc?
>> </Pettiness alert>
>>
>> I ran bigger run twice yesterday and got fitnesses of .8746 and .9086.
>> Unless there's a chance of get a "better-than-perfect" fitness, I guess I
>> should move on to the next level ;).
>>
>>     
>
> <self-criticism-before-anyone-else-says-anything>
> I know why 3-3s-4n-perf.sc is named as was - it was perfect for the 3 step 
> scenario. My petty complaint was that the "hence the name" didn't add up. />
>   
I see now that I misled you with an erroneous sentence.  I said: "It was 
evolved for 3 and 4 steps, hence the name."  But that sentence did not 
correspond with the name.

But now the question is, can you illustrate that ANN with a python 
program for VizANN-4?  It would be helpful if some of the weights can be 
eliminated, and that's prolly the case.  A C program that can do that is 
in the "extras" folder of the 4Play project.  The program is called 
examine.c.  It finds weights that can be zeroed, and then produces an 
equivalent chromosome with those zeroes.  However, you would have to 
modify examine.c to use our current fitness function rather than the one 
from 4 play.  If you want to do this I will help.

m

-- 
I'm proud of http://ANNEvolve.sourceforge.net.  If you want to write software, 
or articles, or do testing or research for ANNEvolve, let me know.  



-------------------------------------------------------------------------
Using Tomcat but need to do more? Need to support web services, security?
Get stuff done quickly with pre-integrated technology to make your job easier
Download IBM WebSphere Application Server v.1.0.1 based on Apache Geronimo
http://sel.as-us.falkag.net/sel?cmd=lnk&kid=120709&bid=263057&dat=121642

Reply via email to