What is Explainable AI?

The field aimed at making machine learning models understandable to humans

A model could reject your application for a mortgage or diagnose you with cancer. These decisions have consequences. Serious consequences. Even if they are correct, we would expect an explanation. To get these we look to the field of explainable AI. 

Read on Medium

 Latest YouTube

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.<br /><br />SHAP course: https://adataodyssey.com/courses/shap-with-python/ <br /><br />Get FREE access: https://mailchi.mp/40909011987b/signup <br /><br />Read the companion article (no-paywall link): <br />https://towardsdatascience.com/interperable-vs-explainable-machine-learning-1fa525e12f48?sk=0394bbace04d1ba96f467ec42ced6d92<br /><br />Medium: https://conorosullyds.medium.com/ <br />Twitter: https://twitter.com/conorosullyDS <br />Mastodon: https://sigmoid.social/@conorosully <br />Website: https://adataodyssey.com/
Interpretable vs Explainable Machine Learning
SHAP is the most powerful Python package for understanding and debugging your machine learning models. Yet, it still has its limitations. Understanding these is critical to avoid incorrect conclusions when using the package. We explore the 4 most significant limitations of SHAP: issues with the package, feature dependencies, causal inference and human error. <br /><br />SHAP course: https://adataodyssey.com/courses/shap-with-python/ <br /><br />Get FREE access: https://mailchi.mp/40909011987b/signup <br /><br />Read the companion article (no-paywall link): https://towardsdatascience.com/the-limitations-of-shap-703f34061d86?sk=cfba01d7efcf8c87d2e5c30d281fbbc6<br /><br />Medium: https://conorosullyds.medium.com/ <br />Twitter: https://twitter.com/conorosullyDS <br />Mastodon: https://sigmoid.social/@conorosully <br />Website: https://adataodyssey.com/
4 Significant Limitations of SHAP
Shapley values come from game theory. So, what do they have to do with machine learning? We understand how the Shapley value formula is extended to explain how each model feature has contributed to a prediction. We will also see that the Shapley value axioms lead to desirable properties for a feature attribution method. To end, we will discuss how Shapley values can be approximated using Monte Carlo sampling, KernelSHAP and TreeSHAP. <br /><br />SHAP course: https://adataodyssey.com/courses/shap-with-python/ <br /><br />Get FREE access: https://mailchi.mp/40909011987b/signup <br /><br />Read the companion article (no-paywall link): https://towardsdatascience.com/from-shapley-to-shap-understanding-the-math-e7155414213b?sk=329a1f042a0167162487f7bb3f0ffd46<br /><br />Medium: https://conorosullyds.medium.com/ <br />Twitter: https://twitter.com/conorosullyDS <br />Mastodon: https://sigmoid.social/@conorosully <br />Website: https://adataodyssey.com/
Shapley Values for Machine Learning
Subscribe
This error message is only visible to WordPress admins

Cannot collect videos from this channel. Please make sure this is a valid channel ID.