Get more out of Explainable AI (XAI): 10 Tips
Вставка
- Опубліковано 31 тра 2024
- Explainable Artificial intelligence (XAI), also known as Interpretable Machine Learning (IML), can explain complex machine learning models. But, the methods are not a golden bullet. You can’t simply fire them at black-box models and expect reasonable explanations for their inner workings. Yet, they can still provide incredible insight if used correctly.
So, I give 10 tips for getting the most out of XAI methods. The tips are roughly divided into 3 groups. The first four tips focus on the underlying data used to train models. The next four focus on you as a user of XAI methods. The last two delve into more technical considerations for XAI Python packages.
🚀 Free Course 🚀
Signup here: mailchi.mp/40909011987b/signup
XAI course: adataodyssey.com/courses/xai-...
SHAP course: adataodyssey.com/courses/shap...
🚀 Companion Article (no-paywall link): 🚀
[coming soon]
🚀 Useful playlists 🚀
XAI: • Explainable AI (XAI)
SHAP: • SHAP
Algorithm fairness: • Algorithm Fairness
🚀 Get in touch 🚀
Medium: / conorosullyds
Threads: www.threads.net/@conorosullyds
Twitter: / conorosullyds
Website: adataodyssey.com/
🚀 Chapters 🚀
00:00 Introduction
01:36 Tip1: Incorporate domain knowledge
03:08 Tip 2: Build intuitive features
04:16 Tip 3: Reduce correlated features
05:55 Tip 4: start with a simple model
06:52 Tip 5: Understand your audience
07:53 Tip 6: Avoid conclusions about causality
08:52 Tip 7: Be aware of confirmation bias
10:12 Tip 8: Use multiple methods
11:03 Tip 9: Use TreeShap
11:58 Tip 10: Python package dependencies
🚀 Free Course 🚀
Signup here: mailchi.mp/40909011987b/signup
XAI course: adataodyssey.com/courses/xai-with-python/
SHAP course: adataodyssey.com/courses/shap-with-python/