Skip to main content
Cross Validated
Alex Punnen's user avatar
Alex Punnen's user avatar
Alex Punnen's user avatar
Alex Punnen
  • Member for 6 years, 11 months
  • Last seen more than a week ago
Profile Activity

27 Actions

All Accepts Posts Badges Comments Revisions Reviews Suggestions
awarded
 Popular Question
answered
What exactly are keys, queries, and values in attention mechanisms?
awarded
 Announcer
awarded
 Yearling
awarded
 Scholar
accepted
Back Propagation Derivation - where am I going wrong
answered
Back Propagation Derivation - where am I going wrong
revised
Back Propagation Derivation - where am I going wrong
added 6293 characters in body; edited tags
asked
Back Propagation Derivation - where am I going wrong
answered
Jacobian Matrix of an Element wise operation on a Matrix
comment
Jacobian Matrix of an Element wise operation on a Matrix
I think that was the problem
comment
Jacobian Matrix of an Element wise operation on a Matrix
I had thought the same, however when implementing taking say a $2*2$ input matrix and writing out the Jacobian matrix in long-form, the dimension of the Jacobian matrix is $8*2$; so the diagonal does not make sense here
asked
Jacobian Matrix of an Element wise operation on a Matrix
comment
What's wrong in this derivation of back-propagation errors?
finally it is getting clear how hadamard product comes in backpropagation equations; Thanks
revised
Backpropagation with Softmax / Cross Entropy
updated
revised
Backpropagation with Softmax / Cross Entropy
added index notation
answered
Backpropagation with Softmax / Cross Entropy
comment
Derivative of Softmax with respect to weights
These two links explained this to me eli.thegreenplace.net/2016/… + stackoverflow.com/a/46028029/429476
comment
In a convolutional neural network (CNN), when convolving the image, is the operation used the dot product or the sum of element-wise multiplication?
Python code for illustration gist.github.com/alexcpn/0378e092d1d6c9a8c432a38bf6cceb37
awarded
 Necromancer
1
2