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 …

A survey on XAI and natural language explanations

E Cambria, L Malandri, F Mercorio… - Information Processing …, 2023 - Elsevier
The field of explainable artificial intelligence (XAI) is gaining increasing importance in recent
years. As a consequence, several surveys have been published to explore the current state …

Explaining any time series classifier

R Guidotti, A Monreale, F Spinnato… - 2020 IEEE second …, 2020 - ieeexplore.ieee.org
We present a method to explain the decisions of black box models for time series
classification. The explanation consists of factual and counterfactual shapelet-based rules …

Principles of explainable artificial intelligence

R Guidotti, A Monreale, D Pedreschi… - Explainable AI Within the …, 2021 - Springer
The last decade has witnessed the rise of a black box society where obscure classification
models are adopted by Artificial Intelligence systems (AI). The lack of explanations of how AI …

Toward the application of XAI methods in EEG-based systems

A Apicella, F Isgrò, A Pollastro, R Prevete - arXiv preprint arXiv …, 2022 - arxiv.org
An interesting case of the well-known Dataset Shift Problem is the classification of
Electroencephalogram (EEG) signals in the context of Brain-Computer Interface (BCI). The …

Exploiting auto-encoders and segmentation methods for middle-level explanations of image classification systems

A Apicella, S Giugliano, F Isgrò, R Prevete - Knowledge-Based Systems, 2022 - Elsevier
A central issue addressed by the rapidly growing research area of eXplainable Artificial
Intelligence (XAI) is to provide methods to give explanations for the behaviours of Machine …

Understanding Any Time Series Classifier with a Subsequence-based Explainer

F Spinnato, R Guidotti, A Monreale, M Nanni… - ACM Transactions on …, 2023 - dl.acm.org
The growing availability of time series data has increased the usage of classifiers for this
data type. Unfortunately, state-of-the-art time series classifiers are black-box models and …

Middle-level features for the explanation of classification systems by sparse dictionary methods

A Apicella, F Isgrò, R Prevete… - International Journal of …, 2020 - World Scientific
Machine learning (ML) systems are affected by a pervasive lack of transparency. The
eXplainable Artificial Intelligence (XAI) research area addresses this problem and the …

Don't Push the Button! Exploring Data Leakage Risks in Machine Learning and Transfer Learning

A Apicella, F Isgrò, R Prevete - arXiv preprint arXiv:2401.13796, 2024 - arxiv.org
Machine Learning (ML) has revolutionized various domains, offering predictive capabilities
in several areas. However, with the increasing accessibility of ML tools, many practitioners …

Factual and counterfactual explanation of fuzzy information granules

I Stepin, A Catala, M Pereira-Fariña… - … Artificial Intelligence: A …, 2021 - Springer
In this chapter, we describe how to generate not only interpretable but also self-explaining
fuzzy systems. Such systems are expected to manage information granules naturally as …