Machine Learning and AI Foundations: Producing Explainable AI (XAI) and Interpretable Machine Learning Solutions

Course details

Data scientists and machine learning professionals have to stay apace with the latest techniques and approaches in the field. In this course, instructor Keith McCormick shows you how to produce explainable AI (XAI) and interpretable machine learning (IML) solutions.

Learn why the need for XAI has been rapidly increasing in recent years. Explore available methods and common techniques for XAI and IML, as well as when and how to use each. Keith walks you through the challenges and opportunities of black box models, showing you how to bring transparency to your models and using real-world examples that illustrate tricks of the trade on the easy-to-learn, open-source KNIME Analytics Platform. By the end of this course, you’ll have a better understanding of XAI and IML techniques for both global and local explanations.

Concepts

Introduction

Exploring the world of explainable AI and interpretable machine learning
Target audience
What you should know

What Are XAI and IML

Understanding the what and why your models predict
Variable importance and reason codes
Comparing IML and XAI
Trends in AI making the XAI problem more prominent
Local and global explanations
XAI for debugging models
KNIME support of global and local explanations

Why Isolating a Variable s Contribution Is Difficult

Challenges of variable attribution with linear regression
Challenges of variable attribution with neural networks
Rashomon effect

Black Box Model 101

What qualifies as a black box
Why do we have black box models
What is the accuracy interpretability tradeoff
The argument against XAI

Introduction to KNIME for XAI and IML

Introducing KNIME
Building models in KNIME
Understanding looping in KNIME
Where to find available KNIME support for XAI

XAI Techniques - Global Explanations

Providing global explanations with partial dependence plots
Using surrogate models for global explanations
Developing and interpreting a surrogate model with KNIME
Permutation feature importance
Global feature importance demo

Techniques for Local Explanations

Developing an intuition for Shapley values
Introducing SHAP
Using LIME to provide local explanations for neural networks
What are counterfactuals
KNIME's Local Explanation View node
XAI View node demonstrating KNIME

IML Techniques

General advice for better IML
Why feature engineering is critical for IML
CORELS and recent trends

Conclusion

Continuing to explore XAI