Updated _base.py #31240
Closed
Updated _base.py #31240
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Clipping function becomes zero when x>30 or x< -30 . So Clipping helps keeping it in a range where gradient flow is non-zero and training can proceed.
|
I think it was decided this was 'not planned' in #31235, but documentation improvement welcome. |
|
okay |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Issue #31235
Clipping function becomes zero when x>30 or x< -30 . So Clipping helps keeping it in a range where gradient flow is non-zero and training can proceed.
This change improves the numerical stability and learning performance of the logistic (sigmoid) activation function used in MLPClassifier and MLPRegressor by clipping the input range to the sigmoid.