[ 3 / biz / cgl / ck / diy / fa / ic / jp / lit / sci / vr / vt ] [ index / top / reports ] [ become a patron ] [ status ]
2023-11: Warosu is now out of extended maintenance.

/sci/ - Science & Math


View post   

File: 280 KB, 1473x1061, 257.jpg [View same] [iqdb] [saucenao] [google]
11266342 No.11266342 [Reply] [Original]

Is there a supervised learning algorithm taking as input stuff like:
- face rating percentile among general population
- frame percentile
- height percentile
- leanness percentile
- muscle mass percentile
- etc
And gives the overall attractiveness percentile as output? Also the explicit function linking those features to attractiveness?
Not just a black box deep learning algorithm that gives ratings to faces...

>> No.11266344

>achieve low body fat/decent amount of muscle
>face suddenly becomes chiseled, visible cheekbones, protruding chin
>8 pack
> v shaped back and shoulders

I already had blue eyes and blond hair tho

>> No.11266345

>>11266344
Those traits are obviously correlated with attractiveness, my question is did we quantify exactly how much they relate to each other?