Interpretability for Industry 4.0 : Statistical and Machine Learning Approaches
Antonio Lepore, Biagio Palumbo, Jean-Michel Poggi
This volume provides readers with a compact, stimulating and multifaceted introduction to interpretability, a key issue for developing insightful statistical and machine learning approaches as well as for communicating modelling results in business and industry.
Different views in the context of Industry 4.0 are offered in connection with the concepts of explainability of machine learning tools, generalizability of model outputs and sensitivity analysis. Moreover, the book explores the integration of Artificial Intelligence and robust analysis of variance for big data mining and monitoring in Additive Manufacturing, and sheds new light on interpretability via random forests and flexible generalized additive models together with related software resources and real-world examples.
Different views in the context of Industry 4.0 are offered in connection with the concepts of explainability of machine learning tools, generalizability of model outputs and sensitivity analysis. Moreover, the book explores the integration of Artificial Intelligence and robust analysis of variance for big data mining and monitoring in Additive Manufacturing, and sheds new light on interpretability via random forests and flexible generalized additive models together with related software resources and real-world examples.
Категории:
Година:
2022
Издателство:
Springer
Език:
english
Страници:
129
ISBN 10:
3031124014
ISBN 13:
9783031124013
Файл:
PDF, 4.68 MB
IPFS:
,
english, 2022
Изтеглянето на тази книга не е възможно поради жалба от притежателя на авторските права