Practical Explainable AI Using Python: Artificial Intelligence Model Explanations Using Python-based Libraries, Extensions, and Frameworks

This book explores the black-box models to boost the adaptability, interpretability, and explainability of AI algorithms using frameworks such as Python XAI libraries, TensorFlow 2.0+, Keras, and custom frameworks using Python wrappers. It covers topics such as model explainability and interpretability basics, ethical consideration, and biases in predictions generated by AI models. It also covers methods and systems to interpret linear, non-linear, and time-series models used in AI, as well as topics ranging from interpreting to understanding how an AI algorithm makes a decision. Additionally, it covers counterfactual explanations for AI models, practical explainable AI using Python, and model explainability for unstructured data, classification problems, and natural language processing-related tasks.

Format: Paperback / softback
Length: 344 pages
Publication date: 15 December 2021
Publisher: APress

This book delves into the intricacies of AI decision-making, biases, and reliability, offering valuable insights into enhancing the adaptability, interpretability, and explainability of AI algorithms. It explores frameworks such as Python XAI libraries, TensorFlow 2.0+, Keras, and custom frameworks using Python wrappers to achieve this goal. The book begins with an introduction to model explainability and interpretability basics, ethical considerations, and biases in AI predictions. It then delves into methods and systems for interpreting linear, non-linear, and time-series models used in AI. The book covers topics ranging from interpreting to understanding how an AI algorithm makes a decision. It also explores ensemble models, explainability, and interpretability using frameworks such as Lime, SHAP, Skater, ELI5, and more. Additionally, the book covers explainability for unstructured data, classification problems, and natural language processing-related tasks. It also examines counterfactual explanations for AI models. Practical Explainable AI Using Python shines the light on deep learning models, rule-based expert systems, and computer vision tasks using various XAI frameworks.

What You'll Learn:

- Review the different ways of making an AI model interpretable and explainable
- Examine the biasness and good ethical practices of AI models
- Quantify, visualize, and estimate reliability of AI models
- Design frameworks to unbox the black-box models
- Assess the fairness of AI models
- Understand the building blocks of trust in AI models
- Increase the level of AI adoption

Who This Book Is For:

AI engineers, data scientists, and software developers involved in driving AI adoption in their organizations.

Weight: 692g
Dimension: 254 x 178 (mm)
ISBN-13: 9781484271575
Edition number: 1st ed.