Neural networks and the derivatives of the cost function

  • Thread starter 2sin54
  • Start date
  • #1
2sin54
109
1
Hello. I need some guidance on the derivation of the derivatives of the quadratic cost function (CF) in an artificial neural network. I can derive the equations for the forward propagation with no trouble but when it comes to finding the derivative of the CF with respect to the weight matrix (matrices) I struggle to distinguish where to use the Hadamar product, where to use the dot matrix product and the order of the multiples. Does anyone know some good resources where I could see a thorough derivation of this OR linear algebra resource relevant to my question?
 

Answers and Replies

  • #2
Edgardo
705
15

Suggested for: Neural networks and the derivatives of the cost function

  • Last Post
Replies
2
Views
516
Replies
18
Views
754
  • Last Post
Replies
2
Views
525
Replies
1
Views
815
  • Last Post
Replies
9
Views
767
Replies
3
Views
560
Replies
0
Views
337
  • Last Post
2
Replies
50
Views
2K
Replies
4
Views
776
Top