how to fix nomalization problem or overfitting

Question

i tried to normalize my data sets column with this code , but the results on the column in (daddr)was not in 0 , 1 range enter image description here and also the results in loss apear like following enter image description here

this is the code i used enter image description here please tell me what is the missing thing to solve the (loss ) problem , how i could do the MinMax Normalization on all data sets column , is the problem overfitting or what ?

score 0 · Answer 1 · answered Feb 09 '23 at 05:30

0

Normalizing the data is not always necessary. It depends with the model you use. Most of the time Normalizing is necessary when working with sigmoid or tanh function in your model. Do you really need to normalize the data ? Try without Normalizing.

answered Feb 09 '23 at 05:30

Shivam Singh

88
7

yes we need to to avoid NaN results in (loss) – الشّيماء عبدالله Feb 09 '23 at 11:24
so i have another thing , do i have to do balance data (oversampling) before or after the normalization ? (i am using all the training set in the deep learning algorithm ) – الشّيماء عبدالله Feb 09 '23 at 11:27

how to fix nomalization problem or overfitting

1 Answers1