Skip to content

Commit

Permalink
Update README.md
Browse files Browse the repository at this point in the history
  • Loading branch information
SkalskiP authored Feb 20, 2020
1 parent 4e22e0f commit 0d3556d
Showing 1 changed file with 2 additions and 1 deletion.
3 changes: 2 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -146,7 +146,7 @@ My posts on the Medium are usually very theoretical - I tend to analyse and desc
</p>

## Knowing What and Why? - Explaining Image Classifier Predictions
Medium articule - [Source code](./02_data_science_toolkit/03_explaining_image_classifier_predictions)
[Medium articule][23] - [Source code](./02_data_science_toolkit/03_explaining_image_classifier_predictions)

As we implement highly responsible Computer Vision systems, it is becoming progressively clear that we must provide not only predictions but also explanations, as to what influenced its decision. In this post, I compared and benchmarked the most commonly used libraries for explaining the model predictions in the field of Image Classification - [Eli5][19], [LIME][20], and [SHAP][21]. I investigated the algorithms that they leverage, as well as compared the efficiency and quality of the provided explanations.

Expand Down Expand Up @@ -198,3 +198,4 @@ This is a place where I collect links to interesting articles and papers, which
[20]: https://github.com/TeamHG-Memex/eli5
[21]: https://github.com/marcotcr/lime
[22]: https://github.com/slundberg/shap
[23]: https://towardsdatascience.com/knowing-what-and-why-explaining-image-classifier-predictions-680a15043bad

0 comments on commit 0d3556d

Please sign in to comment.