Re:Machine learning spots natural selection at work in human...
by ovi256 on Friday November 02, 2018 @06:21AM
(#18361888)
>approaching optimal architectures that do the job but have no superfluous, pre-conceived notions of the (modeled) world
Usually, modelling efficiency is related to the amount of priors. The more (correct) priors, the faster a model learns, and from less data.
A prior-poor model just spends data learning those correct priors in the first place.
There are countless examples I could give to support intuition of this. There isn't, AFAIK, any theoretical work yet.
That the priors are correctly aligned with reality is vital. A model with fixed bad priors cannot unlearn them. If the priors are bad but not fixed, you're just spending time and data to correct those priors.
Usually, modelling efficiency is related to the amount of priors. The more (correct) priors, the faster a model learns, and from less data.
A prior-poor model just spends data learning those correct priors in the first place.
There are countless examples I could give to support intuition of this. There isn't, AFAIK, any theoretical work yet.
That the priors are correctly aligned with reality is vital. A model with fixed bad priors cannot unlearn them. If the priors are bad but not fixed, you're just spending time and data to correct those priors.