Open jozef-mokry opened 8 years ago
It is common not to apply L2 regularization on bias terms. However, from: (https://github.com/nyu-dl/dl4mt-tutorial/blob/master/session3/nmt.py#L1079) it seems that bias terms are included in the regularization. Is this intended?
It is common not to apply L2 regularization on bias terms. However, from: (https://github.com/nyu-dl/dl4mt-tutorial/blob/master/session3/nmt.py#L1079) it seems that bias terms are included in the regularization. Is this intended?