Open adrhill opened 3 years ago
Here's a screenshot of the example in the notebook for quick reference:
Merging #261 (d5bbee1) into master (c6ce893) will not change coverage. The diff coverage is
n/a
.
@@ Coverage Diff @@
## master #261 +/- ##
=======================================
Coverage 71.36% 71.36%
=======================================
Files 41 41
Lines 4173 4173
Branches 637 637
=======================================
Hits 2978 2978
Misses 1007 1007
Partials 188 188
Continue to review full report at Codecov.
Legend - Click here to learn more
Δ = absolute <relative> (impact)
,ø = not affected
,? = missing data
Powered by Codecov. Last update c6ce893...d5bbee1. Read the comment docs.
another reference to add would be
Kohlbrenner et al.: Towards Best Practice in Explaining Neural Network Decisions with LRP
which properly introduces the composite LRP pretty much at the same time as Montavon et al (preprints existed a bit earlier) and evaluates the composite approach against other methods and approaches.
is there anything else I can help with?
is there anything else I can help with?
Is there anything you would change about the example in the screenshot?
maybe add some line(s) actually using this custom built analyzer, and some example heatmaps of this composite rule with non-composite counter parts for comparison?
a hint at the existing LRP presets (if they will be carried over to version 2.0) would also be interesting to the users I guess.
A usage example is already in the notebook. I will add a comparison with the existing presets.
Thanks!
An example on how to use composite LRP is missing from the docs and frequently requested.
Closes #252 Addresses #162, #190, #249, #255
This PR adds a Jupyter notebook explaining how to use the keyword arguments of the
LRP
analyzer class. I'm opening this as a draft PR as we shouldThe references I would add are
Maybe @sebastian-lapuschkin you can help me out here?