I want to create t one-vs.-all a model with a deep neural network in which each output node represents a different class. What loss I can use for this and how to arrange this one vs all scenario. Note that I don’t want to use softmax.
I want to create t one-vs.-all a model with a deep neural network in which each output node represents a different class. What loss I can use for this and how to arrange this one vs all scenario. Note that I don’t want to use softmax.