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

0. Introduction

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

1. What Are XAI and IML

04 - Understanding the what and why your models predict
05 - Variable importance and reason codes
06 - Comparing IML and XAI
07 - Trends in AI making the XAI problem more prominent
08 - Local and global explanations
09 - XAI for debugging models
10 - KNIME support of global and local explanations

2. Why Isolating a Variable s Contribution Is Difficult

11 - Challenges of variable attribution with linear regression
12 - Challenges of variable attribution with neural networks
13 - Rashomon effect

3. Black Box Model 101

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

4. Introduction to KNIME for XAI and IML

18 - Introducing KNIME
19 - Building models in KNIME
20 - Understanding looping in KNIME
21 - Where to find available KNIME support for XAI

5. XAI Techniques - Global Explanations

22 - Providing global explanations with partial dependence plots
23 - Using surrogate models for global explanations
24 - Developing and interpreting a surrogate model with KNIME
25 - Permutation feature importance
26 - Global feature importance demo

6. Techniques for Local Explanations

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

7. IML Techniques

33 - General advice for better IML
34 - Why feature engineering is critical for IML
35 - CORELS and recent trends

Conclusion

36 - Continuing to explore XAI