From the course: Debiasing AI Using Amazon SageMaker
Join today to access over 22,700 courses taught by industry experts or purchase this course individually.
What is explainable AI (XAI)?
From the course: Debiasing AI Using Amazon SageMaker
What is explainable AI (XAI)?
- [Instructor] Complex machine learning models are often considered to be black boxes, which simply means that no one, even the creator of the model, knows why the model made a certain recommendation or prediction. It just simply can't be explained. Explainable AI, or XAI, attempts to rectify the black box problem with machine learning models. The overall goal of XAI is to produce a model that can explain its rationale behind making certain decisions or predictions and call out its own strengths and weaknesses. XAI assists users of the model with knowing what to expect and how the model might perform. The ability to understand why a model chose one path over another path, and the typical errors a model will make, are a huge advancement in machine learning. This level of transparency and explainability helps to build trust in the predictions or outcomes produced by a model. From a legal perspective, in some countries there are now laws that require models to be explainable. Now these…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.