mobeets / nullSpaceControl

1 stars 0 forks source link

anti-pruning #349

Closed mobeets closed 8 years ago

mobeets commented 8 years ago

if amount of learning (say, angle between intuitive mapping and IME for perturbation) predicts less overlap between output-null distributions, does cloud still do well?

maybe do anti-pruning where you ignore all points sampled under similar contexts, to show that cloud is not just good because it's habitual or like a set-difference of distributions predicted by pruning and cloud