After one more day of training the network I described in the previous post slightly decreased the error.
What's interesting, it didn't go to overfitting regime although I used no regularization.
So the final result for this architecture:
What's interesting, it didn't go to overfitting regime although I used no regularization.
So the final result for this architecture:
Test error: 0.1824
Validation error: 0.1451
Train error: 0.1724
Crossentropy during the training:
Error rating during the training:
No comments:
Post a Comment