memory size problem using RI algorithm (windows vista)

[GoogleCodeExporter]

from issue http://code.google.com/p/airhead-research/issues/detail?id=55

When using loading semantic space with RI algorithm:
With 4000 dim  and --usePermutation, output.sspace size is 10M but when I 
suppress --usePermutation option, output.sspace size increase to 300M and 
semantic explorer interpreter cannot load the semantic space !

Without --usePermutation option I have to decrease vector size to 1000 and then 
output.sspace decrease to 70M !

Original issue reported on code.google.com by alain.dh...@gmail.com on 7 Mar 2011 at 1:47

[GoogleCodeExporter]

Which version of random indexing are you using?  I just tested the version in 
the trunk and I'm unable to reproduce this issue.  The permutation function 
slightly increases the .sspace size, which is expected.

Also, how much memory does your machines have?  A 300M .sspace should not be an 
issue for the semantic space explorer, so perhaps your JVM settings are too 
restrictive?  Any information or exceptions you can give us about the issue 
would definitely help. 

  Thanks,
  David

Original comment by David.Ju...@gmail.com on 7 Mar 2011 at 7:04

[GoogleCodeExporter]

Ok  I tried it in June so maybe the new version cannot reproduce it ...

Vista (2Gb RAM)

The problem was output sspace increase from 10M using --usePermutation option 
to 300M  without using it ...

I 'll try to reproduce it. 

Original comment by alain.dh...@gmail.com on 8 Mar 2011 at 9:49