hypeparameters tuning neural network according to loss vs according to scoring function
-
01-11-2019 - |
Question
During hyperparameters tuning we select a metric to measure performance of the model. Example of metrics : f1 score, precision, recall, AUC ...
In general, for the training of neural networks, back-propagation tries to optimize the weights of the model according to the value of the loss function.
Here comes the question: Why don't people use the loss function as a main performance metric for neural networks optimization?
No correct solution
Licensed under: CC-BY-SA with attribution
Not affiliated with datascience.stackexchange