Interpretable vs Explainable Machine Learning
Interpretable models can be understood by a human without any other aids/techniques. On the other hand, explainable models require additional techniques to be understood by humans. We discuss this definition and how it relates to interpretability--the degree to which a model can be understood by a human.
*NOTE*: You will now get the XAI course for free if you sign up (not the SHAP course)
SHAP course: adataodyssey.com/courses/shap...
XAI course: adataodyssey.com/courses/xai-...
Newsletter signup: mailchi.mp/40909011987b/signup
Read the companion article (no-paywall link):
towardsdatascience.com/interp...
Medium: / conorosullyds
Twitter: / conorosullyds
Mastodon: sigmoid.social/@conorosully
Website: adataodyssey.com/
Пікірлер: 21
*NOTE*: You will now get the XAI course for free if you sign up (not the SHAP course) SHAP course: adataodyssey.com/courses/shap-with-python/ XAI course: adataodyssey.com/courses/xai-with-python/ Newsletter signup: mailchi.mp/40909011987b/signup
Great video 🙌
Great explanation. Thanks 👍
@adataodyssey
5 ай бұрын
No problem! I'm glad you found it useful
Great! Thank you
@adataodyssey
6 ай бұрын
No problem! I’m glad you found the video useful :)
Great video, thank you! Thoughts on SHAP vs Explainable boosting classifier?
@adataodyssey
4 ай бұрын
I don't know much about EBC. Will look into it! The major benefit of SHAP and other model agnostic methods is they can be used with any model. This gives you flexibility over model choice which can lead to higher accuracy
Thanks. Just some thoughts from me: It seems to me, that every model could be considered as exaiplainable, because nothing stops you from running your analyzing tool on a simple algorythm, which could be understanded by a human alone without additional tools just by looking at that tree. The question is that whether it's mandatory or optional to use these additional tools to explain this ai logic for us. So if there is such way to call it something like "mandatory to be explained" or something like that but shorter - then I'd rather go with that term. If not - then let it be as it is. Also I don't think you need a gray area there. It's rather a line, but it's not clear. Just like there is not clear definition of junior/middle/senior software developer. One person could be called different grades from this calsification system in different companies. It's very subjective.
@adataodyssey
7 ай бұрын
Some good points Constantine! Goes to show that these definitions are still very debatable. There are hopefully some model where everyone would agree on the definition.
Great video, but I prefer to stick with white-box / black-box categories. I use Interpretable and Explainable interchangebly
@adataodyssey
9 ай бұрын
That's fair! It is less confusing terminology. Interpretable and explainable really mean the same thing to a layperson.
@RyanMcCoppin
6 ай бұрын
@@adataodyssey Sick burn.
whats the color of your eyes?
@adataodyssey
3 ай бұрын
Blue :)
This is where human logic fails, because since our young age, we are trained in Boolean logic paradigm, and not probabilistic / fuzzy logic paradigm. Things are either true or false, while in reality certain things can have a degree of truthiness and falseness.
@adataodyssey
7 ай бұрын
So true! So you’re saying the definition is often a false dichotomy? We probably make the same mistakes when providing explanations for model predictions. Usually they are only one of the many potential reasons for how they work.
Personally, the distinction is not necessary.
@adataodyssey
Ай бұрын
I agree :) But I did think it was important when I first got into XAI.