Search Results for author: Luke Merrick

Found 2 papers, 1 papers with code

Randomized Ablation Feature Importance

no code implementations1 Oct 2019 Luke Merrick

Given a model $f$ that predicts a target $y$ from a vector of input features $\pmb{x} = x_1, x_2, \ldots, x_M$, we seek to measure the importance of each feature with respect to the model's ability to make a good prediction.

Feature Importance

The Explanation Game: Explaining Machine Learning Models Using Shapley Values

1 code implementation17 Sep 2019 Luke Merrick, Ankur Taly

While existing papers focus on the axiomatic motivation of Shapley values, and efficient techniques for computing them, they offer little justification for the game formulations used, and do not address the uncertainty implicit in their methods' outputs.

BIG-bench Machine Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.