Explainable Artificial Intelligence: An Introduction to Interpretable Machine Learning

Explainable Artificial Intelligence: An Introduction to Interpretable Machine Learning Uday Kamath, John Liu
This book takes an in-depth approach to presenting the fundamentals of explainable AI through mathematical theory and practical use cases. The content is split into five parts: 1) pre-hoc techniques involving exploratory data analysis, visualization and feature engineering, 2) intrinsic and interpretable machine learning, 3) model-agnostic methods, 4) explainable deep learning methods and 5) A survey of interpretable and explainable methods applied to time series, natural language processing and computer vision. The field of Explainable AI addresses one of the most significant shortcomings of machine learning and deep learning algorithms today: the interpretability of models. As algorithms become more powerful and make predictions with better accuracy, it becomes increasingly important to understand how and why a prediction is made. Without interpretability and explainability, it would be difficult for the users to trust the predictions of real-life applications of AI. Explainable Artificial Intelligence: AN Introduction to XAI offers its readers a collection of techniques and case studies that serves as an accessible introduction for those entering the field, and for current AI/ML researchers as they integrate explainability into their research and innovation. Categories:
Computers – Artificial Intelligence (AI)
Year:
2021
Publisher:
Springer
Language:
english
Pages:
333
ISBN 10:
3030833550
ISBN 13:
9783030833558
File:
168 MB