Fix deviations from official iRProp- algorithm. #111
+0
−0
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Outdated suggestions cannot be applied.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.
Closes #85.
Closes #110.
The iRProp- algorithm as given in its original paper does not have
weight-backtracking: If the sign of the derivative changes in an
iteration, the weights should not be updated at all.
This PR should not be merged yet, it is still missing a unit test for the new behavior. Unfortunately, I'm a bit lost as to how we could unit-test this change. @andersfylling, do you maybe have an idea?