Covers: application of XAI for Practitioners
Estimated time needed to finish: 60 minutes
Questions this item addresses:
  • How do go about incorporating explainability in the Machine learning development cycle?
  • What are the Pros. and Cons. of some of the most popular explainability techniques? How do you choose the right explanation?
  • What is a good explanation?
  • How do you know if the explanation is useful?
How to use this item?

Watch this video to gain insight from an industry practitioner on how to adopt XAI in a regulated industry

Fail to play? Open the link directly: https://youtube.com/watch?v=8FvCuNJO5a8
Author(s) / creator(s) / reference(s)
Violeta Misheva , Ph.D
0 comment
Recipe
publicShare
Star(0)

XAI for Practitioners

Contributors
Total time needed: ~3 hours
Objectives
XAI refers to methods and models that make ML and predictions understandable to humans. This is of importance to various stakeholders and needed to gain trust and adoption of AI models in high-stakes decisions.
Potential Use Cases
Deploying ML in high stakes decisions
Who is This For ?
INTERMEDIATE
Click on each of the following annotated items to see details.
PAPER 1. Principles and Practice of Explainable Machine Learning
  • What are the evaluation criteria for ML explanations?
  • What are the types of ML explanations?
120 minutes
VIDEO 2. XAI Data Scientist User Journey
  • How do go about incorporating explainability in the Machine learning development cycle?
  • What are the Pros. and Cons. of some of the most popular explainability techniques? How do you choose the right explanation?
  • What is a good explanation?
  • How do you know if the explanation is useful?
60 minutes

Concepts Covered

0 comment