Re:Ethical AI researcher Timnit Gebru fired from Google
by trhway on Thursday December 03, 2020 @03:15AM
(#25286747)
>This is not surprising. Black faces and White faces are not the same data manifold.
in particular because features contrast (dynamic range) is lower for darker faces.
>Is the width of their convolutions racist?
Not width. As a result of the above mentioned lower contrast, the racist here is the sensitivity of the resulting Gabor filters produced by the training in the first convolution layers and the Gauss filters in the next layer's. I suspect to deal with that problem one would have to normalize dynamic range of the faces, i.e. it would look something like kind of lightening of the dark faces and/or darkening of the white ones.
in particular because features contrast (dynamic range) is lower for darker faces.
>Is the width of their convolutions racist?
Not width. As a result of the above mentioned lower contrast, the racist here is the sensitivity of the resulting Gabor filters produced by the training in the first convolution layers and the Gauss filters in the next layer's. I suspect to deal with that problem one would have to normalize dynamic range of the faces, i.e. it would look something like kind of lightening of the dark faces and/or darkening of the white ones.