diff --git a/tutorials/README.md b/tutorials/README.md index abc28118..21020a66 100644 --- a/tutorials/README.md +++ b/tutorials/README.md @@ -78,9 +78,11 @@ Also the main conclusions (🠊) from the thesis (on images and text) about the | $p_{keep}$ | **optimized** (*i*, *txt*), **$0.5$** (*ts*) | $0.1$| $0.1$ | default | $0.1$| $0.1$| | $n_{features}$ |**$8$** | $6$ |default | default | default | $16$ | -🠊 The most crucial parameter is $p_{keep}$. Lower values of $p_{keep}$ lead to more sentitive explanations (observed for both images and text). +🠊 The most crucial parameter is $p_{keep}$. Lower values of $p_{keep}$ lead to more sentitive explanations (observed for both images and text). Easier classificication tasks usually require a lower $p_keep$ as this will cause more perturbation in the input and therefore a more distinct signal in the model predictions. -🠊 The feature resolution $n_{features}$ exhibited an optimum at a value of $6$. +🠊 The feature resolution $n_{features}$ exhibited an optimum at a value of $6$. Higher values can offer a finer grained result but require (far) more $n_masks$. This is also dependent on the scale of the phenomena in the input data that we want to take into account in the explanation. + +🠊 Larger $n_masks$ will return more consistent results at the cost of computation time. If 2 identical runs yield (very) different results, these will likely contain a lot of (or even mostly) noise and a higher value for $n_masks$ should be used instead. #### LIME | Hyperparameter | Default value | LeafSnap30 Logo (*i*) |Weather Logo (*ts*)| Coffe Logo(*ts*)|