use jpeg instead of png

manuscript/05.9-agnostic-shapley.Rmd

@@ -102,7 +102,7 @@ We replace the feature values of features that are not in a coalition with rando
 
 
 ```{r shapley-coalitions, fig.cap = "All 8 coalitions needed for computing the exact Shapley value of the `cat-banned` feature value."}
-knitr::include_graphics("images/shapley-coalitions.png")
+knitr::include_graphics("images/shapley-coalitions.jpg")
 ```
 
 If we estimate the Shapley values for all feature values, we get the complete distribution of the prediction (minus the average) among the feature values.