Counterfactual explanations and how to find them: literature review and benchmarking

R Guidotti - Data Mining and Knowledge Discovery, 2024‏ - Springer
Interpretable machine learning aims at unveiling the reasons behind predictions returned by
uninterpretable classifiers. One of the most valuable types of explanation consists of …

[HTML][HTML] A systematic review of explainable artificial intelligence in terms of different application domains and tasks

MR Islam, MU Ahmed, S Barua, S Begum - Applied Sciences, 2022‏ - mdpi.com
Artificial intelligence (AI) and machine learning (ML) have recently been radically improved
and are now being employed in almost every application domain to develop automated or …

[HTML][HTML] Connecting the dots in trustworthy Artificial Intelligence: From AI principles, ethics, and key requirements to responsible AI systems and regulation

N Díaz-Rodríguez, J Del Ser, M Coeckelbergh… - Information …, 2023‏ - Elsevier
Abstract Trustworthy Artificial Intelligence (AI) is based on seven technical requirements
sustained over three main pillars that should be met throughout the system's entire life cycle …

A survey of contrastive and counterfactual explanation generation methods for explainable artificial intelligence

I Stepin, JM Alonso, A Catala, M Pereira-Fariña - Ieee Access, 2021‏ - ieeexplore.ieee.org
A number of algorithms in the field of artificial intelligence offer poorly interpretable
decisions. To disclose the reasoning behind such algorithms, their output can be explained …

Benchmarking and survey of explanation methods for black box models

F Bodria, F Giannotti, R Guidotti, F Naretto… - Data Mining and …, 2023‏ - Springer
The rise of sophisticated black-box machine learning models in Artificial Intelligence
systems has prompted the need for explanation methods that reveal how these models work …

[HTML][HTML] Deterministic local interpretable model-agnostic explanations for stable explainability

MR Zafar, N Khan - Machine Learning and Knowledge Extraction, 2021‏ - mdpi.com
Local Interpretable Model-Agnostic Explanations (LIME) is a popular technique used to
increase the interpretability and explainability of black box Machine Learning (ML) …

Explainable AI-driven IoMT fusion: Unravelling techniques, opportunities, and challenges with Explainable AI in healthcare

NA Wani, R Kumar, J Bedi, I Rida - Information Fusion, 2024‏ - Elsevier
Abstract Background and Objective: Artificial Intelligence (AI) has shown significant
advancements across several industries, including healthcare, using better fusion …

Bias and discrimination in AI: a cross-disciplinary perspective

X Ferrer, T Van Nuenen, JM Such… - IEEE Technology and …, 2021‏ - ieeexplore.ieee.org
Operating at a large scale and impacting large groups of people, automated systems can
make consequential and sometimes contestable decisions. Automated decisions can impact …

[HTML][HTML] Classification of explainable artificial intelligence methods through their output formats

G Vilone, L Longo - Machine Learning and Knowledge Extraction, 2021‏ - mdpi.com
Machine and deep learning have proven their utility to generate data-driven models with
high accuracy and precision. However, their non-linear, complex structures are often difficult …

Interpretability research of deep learning: A literature survey

B Xua, G Yang - Information Fusion, 2024‏ - Elsevier
Deep learning (DL) has been widely used in various fields. However, its black-box nature
limits people's understanding and trust in its decision-making process. Therefore, it becomes …