New answers tagged loss-function
1
vote
XGBoost custom objective for regression in R
I have a suggestion.
Indeed the methodology is the right one but the problem comes from the definition of your functions.
Since they are not the right ones, they then give the wrong Grad and Hess. The ...
Top 50 recent answers are included
Related Tags
loss-function × 496neural-network × 123
machine-learning × 105
keras × 105
deep-learning × 104
tensorflow × 70
python × 38
classification × 37
regression × 34
cnn × 33
pytorch × 33
lstm × 29
gradient-descent × 27
optimization × 25
training × 21
autoencoder × 21
xgboost × 17
multiclass-classification × 17
accuracy × 16
backpropagation × 14
logistic-regression × 12
convolutional-neural-network × 11
probability × 11
mse × 11
linear-regression × 10