Practical explainable AI using Python : artificial intelligence model explanations using Python-based libraries, extensions, and frameworks

• Main Author: Mishra, Pradeepta
• Format: Electronic eBook
• Language: English
• Published: Berkeley, CA : Apress L.P., 2022.
• Subjects: Python (Computer program language); Artificial intelligence > Data processing.; Application software > Development.; elektronické knihy; electronic books
• ISBN: 9781484271582; 1484271580; 1484271572; 9781484271575
• Physical Description: 1 online resource (356 pages)

Learn the ins and outs of decisions, biases, and reliability of AI algorithms and how to make sense of these predictions. This book explores the so-called black-box models to boost the adaptability, interpretability, and explainability of the decisions made by AI algorithms using frameworks such as...

Table of Contents:

• Chapter 1: Introduction to Model Explainability and Interpretability
• Chapter 2: AI Ethics, Biasness and Reliability
• Chapter 3: Model Explainability for Linear Models Using XAI Components
• Chapter 4: Model Explainability for Non-Linear Models using XAI Components
• Chapter 5: Model Explainability for Ensemble Models Using XAI Components
• Chapter 6: Model Explainability for Time Series Models using XAI Components
• Chapter 7: Model Explainability for Natural Language Processing using XAI Components
• Chapter 8: AI Model Fairness Using What-If Scenario
• Chapter 9: Model Explainability for Deep Neural Network Models
• Chapter 10: Counterfactual Explanations for XAI models
• Chapter 11: Contrastive Explanation for Machine Learning
• Chapter 12: Model-Agnostic Explanations By Identifying Prediction Invariance
• Chapter 13: Model Explainability for Rule based Expert System
• Chapter 14: Model Explainability for Computer Vision.