Explainable artificial intelligence - Wikipedia
5
Public whispers
5
Contributors
2026-07-26 10:02:43
First whispered
Public whispers on this page
Text Highlight2026-07-26 13:23:43
Original Highlight Excerpt
"SHAP (SHapley Additive exPlanations) enables visualization of the contribution of each input feature to the output."
Whisper Note
But doesn't it get super slow with many features?
Text Highlight2026-07-26 13:14:43
Original Highlight Excerpt
"SHAP (SHapley Additive exPlanations) enables visualization of the contribution of each input feature to the output."
Whisper Note
So SHAP is basically game theory for ML, cool.
Text Highlight2026-07-26 10:20:43
Original Highlight Excerpt
"A model is transparent "if the processes that extract model parameters from training data and generate labels from testing data can be described and motivated…"
Whisper Note
I think this is spot on — transparency is about the designer's ability to explain, not just the code.
Text Highlight2026-07-26 10:11:43
Original Highlight Excerpt
"A model is transparent "if the processes that extract model parameters from training data and generate labels from testing data can be described and motivated…"
Whisper Note
So basically if the guy who built it can talk about it, it's transparent? What about everyone else?
Text Highlight2026-07-26 10:02:43
Original Highlight Excerpt
"A model is transparent "if the processes that extract model parameters from training data and generate labels from testing data can be described and motivated…"
Whisper Note
That definition sounds nice but it's like saying a recipe is transparent if the chef can explain it, not if you can
Share this page's whispers
Short link
https://domwhisper.com/s/41712b8d1788Embed snippet
<iframe src="https://domwhisper.com/embed/41712b8d1788" width="100%" height="480" style="border:0;border-radius:16px" loading="lazy"></iframe>See what people are discussing on en.wikipedia.org
Install DomWhisper to view live whispers as you browse, and join the discussion.
Get the extension