Thanks Fergal,

All of them are semantically good and there is no noise in the imput. To
get a better idea, the meaning of the 0 and 1 are control flow changes in a
program execution and micro-architectural instruction level (0 means no
flow change, 1 means flow change).  I'll try and see what happens.


2013/8/6 Fergal Byrne <[email protected]>

>
>  Hi Valentin,
>
>  The inputs to a region are best if they are an SDR (large number of
> bits, maybe 500-2,000, with a sparse on-bit population of say 2%) or a
> sensory representation of say 128 bits with 20-30 bits on at any time. It
> is important in both cases that you have overlapping bits semantically
> significant (so you can subsample the on-bits and still approximate the
> data).
>
>  Less than 4% is fine for input data as long as the 4% is semantically
> good (ie that if the underlying meaning of the data changes semantically by
> 5-10%, only 5-10% of the bits change).
>
>  Regards
>
>  Fergal Byrne
>
> _______________________________________________
> nupic mailing list
> [email protected]
> http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org
>
>


-- 
--
vpuente
_______________________________________________
nupic mailing list
[email protected]
http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org

Reply via email to