Shapley values come from game theory. So, what do they have to do with machine learning? We understand how the Shapley value formula is extended to explain how each model feature has contributed to a prediction. We will also see that the Shapley value axioms lead to desirable properties for a feature attribution method. To end, we will discuss how Shapley values can be approximated using Monte Carlo sampling, KernelSHAP and TreeSHAP.
*NOTE*: You will now get the XAI course for free if you sign up (not the SHAP course)
SHAP course: adataodyssey.c...
XAI course: adataodyssey.c...
Newsletter signup: mailchi.mp/409...
Read the companion article (no-paywall link): towardsdatasci...
Medium: / conorosullyds
Twitter: / conorosullyds
Mastodon: sigmoid.social...
Website: adataodyssey.com/
14 окт 2024