Can a neural Neural network model havehaving high validation loss shows higher accuracy in test set although it has the highestdata during cross validation loss value than others?process

Source Link

asked Mar 29, 2017 at 14:06

Shyamkkhadka

287
1
5
12

Can a neural network model have higher accuracy in test set although it has the highest validation loss value than others?

I am training 3 different models, with varying parameters like learning_rate, regularization_strength. But number of epochs is same for all. For a fixed no. of epoch, model 2 has the highest validation loss value. But the accuracy of it is highest in test set. How can it be possible ? Or I have some bug ?

neural-networks

Stack Exchange Network

Return to Question

Can a neural Neural network model havehaving high validation loss shows higher accuracy in test set although it has the highestdata during cross validation loss value than others?process

Can a neural network model have higher accuracy in test set although it has the highest validation loss value than others?