zenon/trustworthy-ai
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Remove ellipsis

Browse Source
This commit is contained in:
Tobias Eidelpes 2022-01-05 18:13:14 +01:00
parent 663f1316c8
commit 4f58287fe5
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
trustworthy-ai.tex
View File

@ -367,7 +367,7 @@ outcome, the model is inherently explainable. Examples are decision trees,
linear regression models, rule-based models and Bayesian networks. This approach linear regression models, rule-based models and Bayesian networks. This approach
is not possible for neural networks and thus \emph{model-agnostic explanations} is not possible for neural networks and thus \emph{model-agnostic explanations}
have to be found. \textsc{LIME} \cite{ribeiroWhyShouldTrust2016} is a tool to have to be found. \textsc{LIME} \cite{ribeiroWhyShouldTrust2016} is a tool to
find such model-agnostic explanations. \textsc{LIME} works \enquote{…by learning find such model-agnostic explanations. \textsc{LIME} works \enquote{by learning
an interpretable model locally around the prediction} an interpretable model locally around the prediction}
\cite[p.~1]{ribeiroWhyShouldTrust2016}. An advantage of this approach is that \cite[p.~1]{ribeiroWhyShouldTrust2016}. An advantage of this approach is that
\textsc{LIME} is useful for any model, regardless of how it is constructed. Due \textsc{LIME} is useful for any model, regardless of how it is constructed. Due