search

carpentries-incubator / deep-learning-intro

Learn Deep Learning with Python
https://carpentries-incubator.github.io/deep-learning-intro/
Other
30 stars 36 forks source link

Add call-out box on Explainable AI #151

Open dafnevk opened 3 years ago

dafnevk commented 3 years ago

As noted in issue #119 , one of the questions that often comes up is how to get feature importance, or understand better what the model is deciding on in general. There is a lot to say about this topic, so I think we should make a call-out box about it including useful links to resources. I think Episode 4 would be a good place to add this call-out box.

cpranav93 commented 1 year ago

In Dianna, we are currently working to add time-series data-sets for the XAI methods and one of the data-sets we plan to use is the weather data-set from the lesson (in a slightly different sense of predicting seasons). We could add a link to the dashboard of dianna, once it is ready (maybe Q2/3, 2023), to the lesson to give a visual overview of explainable AI and what it shows.

svenvanderburg commented 1 year ago

@cpranav93 you could open an issue for that if you want? And maybe add a picture so that it is clear what it is that you want to add?

cpranav93 commented 1 year ago

@svenvanderburg, unfortunately the dashboard is not ready yet. As I mentioned, in terms of a time frame, this is only possible in Q3 next year. I will open an issue once the dashboard is live and I can provide some images/links.