The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
Interpretable Machine Learning Bridging Performance and Transparency in AI Systems
Abstract
Advances in artificial intelligence (AI) technology, particularly through machine learning and deep learning, have resulted in systems that are highly accurate but often difficult to understand. This article explains the importance of interpretability in AI, especially in the context of critical applications such as healthcare, transportation, and public services. Highlighting the differences between inherently interpretable and “black-box” models, the article reviews methods such as SHAP, LIME, and counterfactual explanations to enhance transparency. It also discusses the challenges of implementing interpretability in smart city environments based on IoT and edge computing, as well as its relation to ethics, cybersecurity, and regulations such as GDPR. The article emphasizes that interpretability is not just a technical feature, but an ethical and social foundation for building fair, transparent, and trustworthy AI systems.
Related Content
|
Frederic Andres.
© 2027.
14 pages.
|
|
Kalsoom Safdar, Khairul Najmy Abdul Rani, Mohd Aminudin Jamlos, Siti Julia Rosli, Muhammad Usman Younus, Zanab Safdar.
© 2027.
27 pages.
|
|
Bani Adam, Binastya Anggara Sekti, Muhammad Adi Zacky Zahran.
© 2027.
24 pages.
|
|
Swetha Margaret T. A., Renuka Devi D..
© 2027.
31 pages.
|
|
Maurice Saluschke, Michael Schulz.
© 2027.
30 pages.
|
|
Mirjam Sepesy Maučec, Gregor Donaj.
© 2027.
16 pages.
|
|
Jorge A. Ruiz-Vanoye, Ocotlan Diaz-Parra, Ricardo A. Barrera-Cámara, Alejandro Fuentes-Penna, Francisco R. Trejo-Macotela, Jaime Aguilar-Ortiz, Eric Simancas-Acevedo.
© 2027.
21 pages.
|
|
|