ravenscroftj
/
brainsteam.co.uk
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

some more typos
continuous-integration/drone/push Build is passing Details

This commit is contained in:
James Ravenscroft 2022-01-17 14:37:37 +00:00
parent 3e7527333c
commit 70338adbef
1 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
brainsteam/content/posts/2022/01/13-01-painless-explainability-for-text-models-with-eli5/index.md
View File

@ -46,13 +46,12 @@ The local aspect of LIME is described in [the paper](https://arxiv.org/abs/1602.
> ...Although it is often impossible for an explanation to be completely faithful unless it is the complete description of the model itself, for an explanation to be meaningful it must at least be locally faithful, i.e. it must correspond to how the model behaves in the vicinity of the instance being predicted... > ...Although it is often impossible for an explanation to be completely faithful unless it is the complete description of the model itself, for an explanation to be meaningful it must at least be locally faithful, i.e. it must correspond to how the model behaves in the vicinity of the instance being predicted...
> >
This is a really important constraint of LIME: it offers excellent example-specific explanations that work well for pockets of similar data points but these explanations can't necessarily be generalised for the whole of the model under examination. The authors of the paper also attempt to illustrate this limitation in a diagram: This is a really important constraint of LIME: it offers excellent example-specific explanations that work well for pockets of similar data points but these explanations can't necessarily be generalised for the whole of the model under examination. The authors of the paper also attempt to illustrate this limitation in a diagram:
{{<figure src="images/figure3.png" caption="Figure 3 from the [Ribeiro et al](https://arxiv.org/abs/1602.04938) attempts to illustrate how LIME can offer explanations within a local neighbourhood of data samples">}} {{<figure src="images/figure3.png" caption="Figure 3 from the [Ribeiro et al](https://arxiv.org/abs/1602.04938) attempts to illustrate how LIME can offer explanations within a local neighbourhood of data samples">}}
#### To Spam or not to spam: that is the question
This is especially important in tasks that are highly context dependent (like text classification). Here's a contrived example of a spam detection use case. Take the words "7 million usd" as in: This is especially important in tasks that are highly context dependent (like text classification). Here's a contrived example of a spam detection use case. Take the words "7 million usd" as in: