Artificial intelligence (AI) and machine learning (ML) impact our lives in many ways. From mundane tasks to critical decision-making processes, AI's role is becoming more central. As a result, the need for transparency and interpretability of these systems is growing. This is why we need to field of Expianable AI (XAI) also known as interpretable machine learning (IML).

We will take a brief look at what XAI aims to achieve and the various approaches at our disposal. These include intrinsically interpretable models, model agnostic methods, causal models, counterfactuals, adversarial examples and non-agnostic methods.

🚀 Free Course 🚀
Signup here: mailchi.mp/40909011987b/signup
XAI course: adataodyssey.com/courses/xai-with-python/
SHAP course: adataodyssey.com/courses/shap-with-python/

🚀 Companion Article (no-paywall link): 🚀
medium.com/data-science/what-is-interpretable-mach…

🚀 Useful playlists 🚀
XAI:    • Explainable AI (XAI)  
SHAP:    • SHAP  
Algorithm fairness:    • Algorithm Fairness  

🚀 Get in touch 🚀
Medium: conorosullyds.medium.com/
Threads: www.threads.net/@conorosullyds
Twitter: twitter.com/conorosullyDS
Website: adataodyssey.com/

🚀 Chapters 🚀
00:00 Introduction
02:15 What is XAI?
03:16 Inrinsically interpretable models
05:14 Black-box models
06:38 Model agnostic methods
07:52 Causal models
08:31 Counterfactual explanations
09:14 Adversarial examples
10:03 Model-specific methods
10:54 A note on t