Explainable AI: Demystifying Complex Models with Shapley Values

Neeraj Pandey

Neeraj Pandey

Neeraj is a polyglot and open-source contributor. Over the years, he has spoken at multiple international Python conferences and has worked on a variety of full-stack software and data science applications, as well as computational arts and quantitative finance projects. He enjoys the challenge of creating new tools and applications.

    摘要

    Explainable artificial intelligence (XAI) refers to AI systems that can clearly and understandably explain their decisions and actions. This is crucial for ensuring that AI systems are transparent, accountable, and trustworthy, and do not make biased or discriminatory decisions. Python offers various libraries that can be used to improve the interpretability of AI algorithms in a variety of situations, such as enhancing transparency in decision-making systems or facilitating communication between AI experts and non-experts. In this hands-on tutorial, you will learn how to use these tools to improve the interpretability of AI algorithms in Python, and explore key metrics and evaluation methods for measuring the effectiveness of XAI techniques. By the end of this tutorial, you will have a better understanding of how to make your AI systems more transparent and trustworthy.

    說明

    地點

    R3

    時間

    第一天 • 13:00-14:30 (GMT+8)

    語言

    英文演講

    層級

    中階

    分類

    機器學習