aboutsummaryrefslogtreecommitdiff
path: root/posts
diff options
context:
space:
mode:
authorYuchen Pei <me@ypei.me>2018-12-03 10:13:19 +0100
committerYuchen Pei <me@ypei.me>2018-12-03 10:13:19 +0100
commit4b72dd514e0f57cd256c0f74832ccb975dc782e6 (patch)
tree2565830bf897b88683e12e54ab65acc616669aec /posts
parent23a7b0321d57e8bed5424d8637982eb9685d60ae (diff)
minor
Diffstat (limited to 'posts')
-rw-r--r--posts/2018-12-02-lime-shapley.md1
1 files changed, 1 insertions, 0 deletions
diff --git a/posts/2018-12-02-lime-shapley.md b/posts/2018-12-02-lime-shapley.md
index c9ada5b..233de19 100644
--- a/posts/2018-12-02-lime-shapley.md
+++ b/posts/2018-12-02-lime-shapley.md
@@ -294,6 +294,7 @@ interpretable by themselves.
One may argue that perhaps we do not need linearity to define $v(S)$ as in (9).
If we do so, however, then (9) loses mathematical meaning.
A bigger question is: how effective is SHAP?
+An even bigger question: in general, how do we evaluate models of interpretation?
Evaluating SHAP
---------------