What makes Z-score std a little bit better in unit 3.7 Feature Normalization (Parts 1-2). #47
Answered
by
rasbt
jihobak
asked this question in
Lecture videos and quizzes
-
From my understanding, It might be ... there are more chance to get gradient from both sides (+), (-) because of zero centering? |
Beta Was this translation helpful? Give feedback.
Answered by
rasbt
May 11, 2023
Replies: 1 comment 1 reply
-
Yes that's right. You can have positive and negative values with the gradient and the weights. So there are 4 different settings negative weight & negative input, negative weight & positive input, positive weight & negative input, positive weight & positive input. If you normalize to [0, 1] range, you can only have negative weight & positive input, and positive weight & positive input. |
Beta Was this translation helpful? Give feedback.
1 reply
Answer selected by
jihobak
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Yes that's right. You can have positive and negative values with the gradient and the weights. So there are 4 different settings negative weight & negative input, negative weight & positive input, positive weight & negative input, positive weight & positive input. If you normalize to [0, 1] range, you can only have negative weight & positive input, and positive weight & positive input.