|
|
|
|
|
|
by sdenton4
613 days ago
|
|
|
The softmax value y is a linear combination of the vectors you're attending over:
y = a1v1 + a2v2 + ... + an*vn
where a_i >= 0 and sum(a_i) = 1. Then y is a convex combination of the v_i, and sits in the convex hull of the v_i. |
|
|