Different Views of Interpretability

Bertrand Iooss (), Ron Kenett () and Piercesare Secchi ()
Additional contact information
Bertrand Iooss: Chatou and SINCLAIR AI Lab, EDF R&D
Ron Kenett: KPA Group and Samuel Neaman Institute
Piercesare Secchi: Department of Mathematics

Chapter Chapter 1 in Interpretability for Industry 4.0: Statistical and Machine Learning Approaches, 2022, pp 1-20 from Springer

Abstract: Abstract Interpretability, in the context of machine learning, means understanding the predictions made by the machine learning algorithm, with the aim to support human decisions based on them. In this view, interpretability can involve identifying the input features which drive the predictions. This chapter develops different issues and related methodologies of interpretability of machine learning models. Their implication for scientific and industrial studies are firstly developed. Then, the links between the generalizability of model outputs and interpretability are discussed. Finally, the deep connection between the settings of the machine learning interpretability and the ones of the model output sensitivity analysis is described.

Date: 2022
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-031-12402-0_1

Ordering information: This item can be ordered from
http://www.springer.com/9783031124020

DOI: 10.1007/978-3-031-12402-0_1

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().