Skip to main content
Sid's user avatar
Sid's user avatar
Sid's user avatar
Sid
  • Member for 10 years, 5 months
  • Last seen more than 1 year ago
awarded
awarded
awarded
awarded
awarded
awarded
awarded
awarded
awarded
awarded
comment
CNN or other for Tree Species Identification in Boreal
Is your hypothesis that for a given image, will there be predominantly 1 tree species?
Loading…
comment
Why not normalizing filters in convolutional networks
Not exactly. In the first case, (the equality) the dual variable can be positive or negative and in the latter it has to be strictly positive. The form of the equations will be the same. But, with the inequality constraint the minima is less than or equal to that with the equality constraint
revised
Loading…
comment
Why not normalizing filters in convolutional networks
Ahh! Im so sorry..Premature jump to conclusion :). Is this what you are looking for?
revised
Loading…
Loading…
answered
Loading…
revised
Gradient ascent to maximise log likelihood
added 104 characters in body
Loading…
answered
Loading…
1
2 3 4 5
15