Book Image

Applied Machine Learning Explainability Techniques

By : Aditya Bhattacharya
Book Image

Applied Machine Learning Explainability Techniques

By: Aditya Bhattacharya

Overview of this book

Explainable AI (XAI) is an emerging field that brings artificial intelligence (AI) closer to non-technical end users. XAI makes machine learning (ML) models transparent and trustworthy along with promoting AI adoption for industrial and research use cases. Applied Machine Learning Explainability Techniques comes with a unique blend of industrial and academic research perspectives to help you acquire practical XAI skills. You'll begin by gaining a conceptual understanding of XAI and why it's so important in AI. Next, you'll get the practical experience needed to utilize XAI in AI/ML problem-solving processes using state-of-the-art methods and frameworks. Finally, you'll get the essential guidelines needed to take your XAI journey to the next level and bridge the existing gaps between AI and end users. By the end of this ML book, you'll be equipped with best practices in the AI/ML life cycle and will be able to implement XAI methods and approaches using Python to solve industrial problems, successfully addressing key pain points encountered.

Related Content you might be interested in

Current Title:

Small book image
Applied Machine Learning Explainability Techniques
Aditya Bhattacharya
Jul, 2022 | 306 pages
Small book image
Deep Learning and XAI Techniques for Anomaly Detection
Cher Simon
Jan, 2023 | 218 pages
Small book image
Interpretable Machine Learning with Python
Serg Masís
Oct, 2023 | 606 pages
Small book image
Interpretable Machine Learning with Python
Serg Masís
Mar, 2021 | 736 pages
Table of Contents (16 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Download the example code files
Download the color images
Conventions used
Get in touch
Share Your Thoughts
1
Section 1 – Conceptual Exposure
Section 1 – Conceptual Exposure
Free Chapter
2
Chapter 1: Foundational Concepts of Explainability Techniques
Chapter 1: Foundational Concepts of Explainability Techniques
Introduction to XAI
Defining explanation methods and approaches
Evaluating the quality of explainability methods
Summary
References
3
Chapter 2: Model Explainability Methods
Chapter 2: Model Explainability Methods
Technical requirements
Types of model explainability methods
Knowledge extraction methods
Result visualization methods
Influence-based methods
Example-based methods
Summary
References
4
Chapter 3: Data-Centric Approaches
Chapter 3: Data-Centric Approaches
Technical requirements
Introduction to data-centric XAI
Thorough data analysis and profiling process
Monitoring and anticipating drifts
Checking adversarial robustness
Measuring data forecastability
Summary
References
5
Section 2 – Practical Problem Solving
Section 2 – Practical Problem Solving
6
Chapter 4: LIME for Model Interpretability
Chapter 4: LIME for Model Interpretability
Technical requirements
Intuitive understanding of LIME
What makes LIME a good model explainer?
SP-LIME
A practical example of using LIME for classification problems
Potential pitfalls
Summary
References
7
Chapter 5: Practical Exposure to Using LIME in ML
Chapter 5: Practical Exposure to Using LIME in ML
Technical requirements
Using LIME on tabular data
Explaining image classifiers with LIME
Using LIME on text data
LIME for production-level systems
Summary
References
8
Chapter 6: Model Interpretability Using SHAP
Chapter 6: Model Interpretability Using SHAP
Technical requirements
An intuitive understanding of the SHAP and Shapley values
Model explainability approaches using SHAP
Using SHAP to explain regression models
Advantages and limitations of SHAP
Summary
References
9
Chapter 7: Practical Exposure to Using SHAP in ML
Chapter 7: Practical Exposure to Using SHAP in ML
Technical requirements
Applying TreeExplainers to tree ensemble models
Explaining deep learning models using DeepExplainer and GradientExplainer
Model-agnostic explainability using KernelExplainer
Exploring LinearExplainer in SHAP
Explaining transformers using SHAP
Summary
References
10
Chapter 8: Human-Friendly Explanations with TCAV
Chapter 8: Human-Friendly Explanations with TCAV
Technical requirements
Understanding TCAV intuitively
Exploring the practical applications of TCAV
Advantages and limitations
Potential applications of concept-based explanations
Summary
References
11
Chapter 9: Other Popular XAI Frameworks
Chapter 9: Other Popular XAI Frameworks
Technical requirements
DALEX
Explainerdashboard
InterpretML
ALIBI
DiCE
ELI5
H2O AutoML explainers
Quick comparison guide
Summary
References
12
Section 3 –Taking XAI to the Next Level
Section 3 –Taking XAI to the Next Level
13
Chapter 10: XAI Industry Best Practices
Chapter 10: XAI Industry Best Practices
Open challenges of XAI
Guidelines for designing explainable ML systems
Adopting a data-first approach for explainability
Emphasizing IML for explainability
Emphasizing prescriptive insights for explainability
Summary
References
14
Chapter 11: End User-Centered Artificial Intelligence
Chapter 11: End User-Centered Artificial Intelligence
User-centered XAI/ML systems
Rapid XAI prototyping using EUCA
Efforts toward increasing user acceptance of AI/ML systems using XAI
Providing a delightful UX
Summary
References
Why subscribe?
15
Other Books You May Enjoy
Other Books You May Enjoy
Packt is searching for authors like you
Share Your Thoughts

InterpretML

InterpretML (https://interpret.ml/) is an XAI toolkit from Microsoft. It aims to provide a comprehensive understanding of ML models for the purpose of model debugging, outcome explainability, and regulatory audits of ML models. With this Python module, we can either train interpretable glassbox models or explain black-box models.

In Chapter 1, Foundational Concepts of Explainability Techniques, we discovered that some models such as decision trees, linear models, or rule-fit algorithms are inherently explainable. However, these models are not efficient for complex datasets. Usually, these models are termed glass-box models as opposed to black-box models, as they are extremely transparent.

Microsoft Research developed another algorithm called Explainable Boosting Machine (EBM), which introduces modern ML techniques such as boosting, bagging, and automatic interaction detection into classical algorithms such as Generalized Additive Models (GAMs). Researchers have...

Previous Section
End of Section 5
Next Section