Interpretability Challenges in Machine Learning Models

This record corresponds to the published book chapter of the following contribution:

"Interpretability Challenges in Machine Learning Models"

This chapter analyzes the growing importance of interpretability in Machine Learning systems, particularly in contexts where algorithmic decisions have significant social, legal, and ethical implications. It reviews the historical evolution of Machine Learning and Deep Learning models, emphasizing the limitations of black-box approaches and the need for transparent and explainable alternatives. The work discusses interpretability challenges from multiple perspectives, including scientific research, industry applications, regulatory frameworks, and public policy. Overall, the chapter provides a structured overview of why interpretability has become a central requirement for responsible and trustworthy Artificial Intelligence.

The published version is available via the publisher and Dialnet:
https://dialnet.unirioja.es/servlet/articulo?codigo=8036858

This deposit is made for open access and dissemination purposes.