![](https://ccweb.imgix.net/https%3A%2F%2Fwww.classcentral.com%2Fimages%2Ficon-black-friday.png?auto=format&ixlib=php-4.1.0&s=fe56b83c82babb2f8fce47a2aed2f85d)
Overview
![](https://ccweb.imgix.net/https%3A%2F%2Fwww.classcentral.com%2Fimages%2Ficon-black-friday.png?auto=format&ixlib=php-4.1.0&s=fe56b83c82babb2f8fce47a2aed2f85d)
This course aims to help learners understand the importance of trust in Artificial Intelligence (AI) systems, especially in critical domains like healthcare and finance. By exploring Explainable AI (XAI), participants will learn how to make AI models more transparent and trustworthy through providing explanations for their predictions. The course covers topics such as different types of explanations, fairness, trust, and the TrustyAI initiative at Red Hat. The teaching method includes theoretical discussions, practical examples, and references for further exploration. This course is intended for individuals interested in AI ethics, transparency, and accountability, particularly those working with AI systems in impactful industries.
Syllabus
Intro
Artificial Intelligence
Problems with AI
Right of explanation
Different type of explanation
Local explanation
Knowledgeable explanation
Minimize if possible
Use a science method
Fairness
Trust AI
Cogito
Microservices
Monitoring
Library
References
QA
Explainability
Extracting explanations
Is explainability important
Theoretical work on explainability
Taught by
Devoxx