nataraj chakraborty wrote:
> May be you are right... I'll use a fixed configuration first.. get 
> evrything right and than add variables... just tell me in 4 play what 
> is typicall size of nets for good results.... I guess I can run that 
> and see right.... or .ini file... ok I'll check out...
I suggest you start with the same number of neurons as in the released 
version.  Then try a couple of larger values.  The SCRA is supposed to 
allow more neurons while having shorter chromosomes.

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.  


-------------------------------------------------------------------------
Take Surveys. Earn Cash. Influence the Future of IT
Join SourceForge.net's Techsay panel and you'll get the chance to share your
opinions on IT & business topics through brief surveys -- and earn cash
http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV

Reply via email to