I did those slides for a talk at school at the very last minute and I did not expect it to be republished. I requested the edit rights on the document and I'll fix this asap.
The transfer function is applied only at evaluation. In the formulas of the slides (and in the code), for training I compute the loss of an example X and it's expected target as: L(XW, target) What you define is…
"the loss function max(0, -xy) is 0 if x and y are the same class and 1 if they are different" Not exactly because this would be optimizing the number of correctly classified elements. Instead you minimize the sum of…
- Is the term 'error function' used as a special function (like sin, cosine, etc) or is it a generalized term ? For backpropagation I call "error function" a function which takes the training data and the parameters of…
I did those slides for a talk at school at the very last minute and I did not expect it to be republished. I requested the edit rights on the document and I'll fix this asap.
The transfer function is applied only at evaluation. In the formulas of the slides (and in the code), for training I compute the loss of an example X and it's expected target as: L(XW, target) What you define is…
"the loss function max(0, -xy) is 0 if x and y are the same class and 1 if they are different" Not exactly because this would be optimizing the number of correctly classified elements. Instead you minimize the sum of…
- Is the term 'error function' used as a special function (like sin, cosine, etc) or is it a generalized term ? For backpropagation I call "error function" a function which takes the training data and the parameters of…