Boosting in HTM and new ways

[rhyolight]

@abshej

When you imply increased in efficiency, you are referring to the inclusion of additional semantic information using boosting, right?

No, I’m talking about spreading the meaning out to more minicolumns in the SP, not the inclusion of more semantic info. The efficiency means there is less overloading of meaning in the used minicolumns because more minicolumns are used. The storage of meaning stays the same, it is just spread out.

@abshej

I suppose there is no such instability due to SDR properties and effect of Boosting being gradual?

I’m not sure what you mean. Boosting does not introduce instability.

@abshej

Could you describe the boost factor algorithm? Is it published?

Introduce new spatial pooler boosting rule (breaking change)

I have implemented a new boosting rule in the HTM spatial pooler (SP). Boosting in SP encourages efficient use of columns by applying a multiplicative factor to the inputs of each column. We call this the boost factor and update it according to the activation history of individual columns (activeDutyCycle). In the old boosting rule, boosting factors are always >=1.0. We increase boost factors for “weak” columns (controlled by the parameter minPctActiveDutyCycles). The strength of boosting is co…