Re:Decoding the Thought Vector
by yxhuvud on Wednesday November 30, 2016 @07:11AM
(#13070060)
Did you ever compare that focus with a graph over the singular values?
[ Parent
| on HN ]
It's a good question, FWIW I would expect a reasonably sharp "L" shaped curve in the focus. The assumption there I guess being that this metric of 'focus' is something well characterized by low-frequency type basis matrices given by the first few rows/columns of the SVD's U and V.