Hi Christian,

What you describe is done in lines 58-60:

58. else if predictiveState(c, i, t) == 0 and predictiveState(c, i, t-1)==1
then
59. adaptSegments (segmentUpdateList(c,i), false)
60. segmentUpdateList(c, i).delete()

If the cell was predictive at t-1 but is no longer predictive (and we know
that it's not active either, because otherwise it would be a learning cell
since it was previously predictive), then adaptSegments() is called with
positiveReinforcement set to false, causing the synapses that were active
(that made the cell predictive at t-1) to be decremented.

-Mike

_____________
Michael Ferrier
Department of Cognitive, Linguistic and Psychological Sciences, Brown
University
[email protected]


On Wed, Jan 29, 2014 at 9:10 PM, Christian Cleber Masdeval Braz <
[email protected]> wrote:

>
>  Hi
>
>  I was studying the TP algorithm and didn't understand one point.
>
>  In the beginning, permanence values are assigned aleatory to distal
> dendrites segments of all cells (as in the initialization of the SP).
>
>  In time t, the region predicts a bunch of cells based on the activation
> of their segments. A segment is active if it have a minimum number of
> active synapses connected with active cells in time t. In time t + 1, the
> cells that were predicted and are in active columns (and just that in
> active columns) will have their synapses permanence values updated
> according.
>
>  But, what about the false positives, the cells that were predicted
> ocasionaly just because they had an active segment that fit well with input
> in time t, but they never occur. Don't they will be predicted again and
> again when the input in time t occur? I couldn't see where the algorithm
> treat this issue.
>
>  In the last part, it does
>
> for c, i in cells
> 55. if learnState(c, i, t) == 1 then                                =>
> update just the cells that are in an active column
> 56. adaptSegments (segmentUpdateList(c, i), true)
> 57. segmentUpdateList(c, i).delete()
>
> Doesn't necessary to decrement the permanence value of those connected
> synapses in the distal dentrite segments of cells that  don't occur?
>
>
> Christian
>
>
>
>
>
>
>
>
>
>
> _______________________________________________
> nupic mailing list
> [email protected]
> http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org
>
>
_______________________________________________
nupic mailing list
[email protected]
http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org

Reply via email to