Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence

Ali, Sajid; Abuhmed, Tamer; El–Sappagh, Shaker; Muhammad, Khan; Alonso-Moral, Jose M.; Confalonieri, Roberto; Guidotti, Riccardo; Ser, Javier Del; Díaz-Rodríguez, Natalia; Herrera, Francisco

doi:10.1016/j.inffus.2023.101805

Cited by 285 publications

(86 citation statements)

References 242 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Measuring diverse XAI methods -More recently, many researchers have questioned the efficacy of current quantitative usercentric metrics to compare different XAI methods [3,28,35]. Most of these metrics are highly subjective to the research participants and do not provide a generalised evaluation of different types of XAI methods for other users or applications.…”

Section: Future Workmentioning

confidence: 99%

Towards Directive Explanations: Crafting Explainable AI Systems for Actionable Human-AI Interactions

Bhattacharya

2024

Extended Abstracts of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Figure 1: This research focuses on crafting Explainable AI systems for actionable human-AI interactions. Considering the current progress, the author conducted three research studies: (1) Combining diverse visual XAI methods in an explanation dashboard, (2) Explanatory model steering with domain experts through a healthcare-focused XAI system, and (3) Data-centric model steering through manual and automated configuration of training data.

show abstract

Section: Future Workmentioning

confidence: 99%

Towards Directive Explanations: Crafting Explainable AI Systems for Actionable Human-AI Interactions

Bhattacharya

2024

Extended Abstracts of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…Therefore, great efforts have been made to develop methods for ML model explanation, so‐called explainable artificial intelligence (XAI). Using these XAI methods, models with high complexity and high flexibility can also take advantage of high interpretability (Ali et al., 2023).…”

Section: Introductionmentioning

confidence: 99%

Can eXplainable AI Offer a New Perspective for Groundwater Recharge Estimation?—Global‐Scale Modeling Using Neural Network

Jung,

Saynisch‐Wagner,

Schulz

2024

Water Resources Research

View full text Add to dashboard Cite

Due to the difficulties in estimating groundwater recharge and cross‐boundary nature of many aquifers, estimating groundwater recharge at large scale has been called upon. Process‐based models as well as data‐driven models have been established to meet this need. Meanwhile, with the advent of explainable artificial intelligence (XAI) methods, data‐driven machine learning models can take advantage of enhanced explainability while keeping the strength of high flexibility. In this study, an ensemble neural network model was built to check the suitability of the model to predict groundwater recharge and the possibility to gain new insights from large data set. Recent large inputs of groundwater recharge data and additional input for the Arabian Peninsula collated in this study were fed to the model with multiple predictors related to climatology considering seasonality, soil and plant characteristics, topography, and hydrogeology. The model showed higher performance (adjusted R2: 0.702, RMSE: 193.35 mm yr−1) than a recent global process‐based model in predicting groundwater recharge. Using XAI methods as individual conditional expectations and Shapley Additive Explanation interaction values, the model behavior was analyzed and possible linear and non‐linear relationships between the predictors and the groundwater recharge rate were found. Long‐term averaged precipitation and enhanced vegetation index showed non‐linear relationships with groundwater recharge rate, while slope, compound topographic index, and water table depth showed low importance to the model results. Most model behaviors followed the domain knowledge, while multi‐correlation between predictors and data skewness hindered the model from learning.

show abstract

“…Automatic, high-accuracy classification and insights gained from resulting, distinctive features would enable us to better understand the BATS phenomenon and basic mechanism of tinnitus on the neural level. Explainable AI has the potential to surpass traditional analysis methods by enabling a comprehensive examination of models and important features [37]. Furthermore, this approach could foster (objective) diagnostic options, tinnitus subtyping, and identification of individual treatment options like sound therapies [38].…”

Section: Introductionmentioning

confidence: 99%

Prediction of acoustic tinnitus suppression using resting state EEG: An explainable AI approach

Shabestari,

Schoisswohl,

Wellauer

et al. 2024

Preprint

View full text Add to dashboard Cite

Tinnitus, characterized by the perception of sound without an external source, affects a significant portion of the population and can lead to considerable individual suffering, yet understanding of its suppression remains limited. Understanding neural traits of tinnitus suppression may be crucial for developing accurate predictive models in tinnitus research and treatment. This study aims to classify individuals capable of brief acoustic tinnitus suppression (BATS; also known as residual inhibition) based on their independent resting state EEG (n=102), exploring the classification’s robustness on various sample splits, and the relevance of resulting specific EEG features in the spirit of explainable AI. A comprehensive set of EEG features, including band power in standard frequency bands, spectral entropy, aperiodic slope and offset of the power spectrum, and connectivity, was included in both sensor and source space. Binary classification of the BATS status was performed using a comprehensive set of standard classifiers and Pearson correlation for feature selection, which addresses multicollinearity, avoiding complex dimensionality reduction techniques. Feature importance was assessed using Gini impurity metrics, allowing interpretation of the directionality of identified neural features. The Random Forest model showed the most consistent performance, with its majority voting mechanism effectively reducing overfitting and providing reliable predictions, and was therefore chosen for subsequent feature interpretation analysis. Our classification task demonstrated high accuracy across the various BATS split thresholds, suggesting that the choice of threshold does not significantly influence the underlying pattern in the data. We achieved classification accuracies of 98% for sensor and source models and 86% for the connectivity model in the main split. Looking at identified important features, our findings align with and extend existing neuroscience research in tinnitus by discovering highly specific and novel neural features in naive resting-state data predictive of BATS. Gamma power is identified as the most important feature in the sensor model, followed by alpha power, which fits current models of sensory processing, prediction, and updating (gamma) as well as inhibitory (alpha) frameworks. The overall spectral shape of the EEG power spectrum tends to be more normal in +BATS individuals, as reflected in the aperiodic offset and slope features. In the source model, important features are lateralized in that the gamma feature is more prominent in the left core auditory network, whereas the alpha feature is distributed more sparsely over the right hemisphere in line with auditory attention data. Furthermore, we identified several hotspots in the temporal, insular, parietal, parahippocampal, medial prefrontal, and (posterior) cingulate cortex implicated in sensory processing, gating, attention, and memory processes. Relevant network features were found in a hyperconnected bilateral auditory network (within the network), while the full auditory network was hyperconnected to limbic regions (between networks), which may reflect an intact sensory gating mechanism aiding tinnitus suppression. This study’s implications extend to improving the understanding and prediction of tinnitus loudness perception and tinnitus distress as well as its (acoustic) suppression. Furthermore, our approach underscores the importance of careful feature selection, model choice, and validation strategies in analyzing complex neurophysiological data.

show abstract

Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence

Cited by 285 publications

References 242 publications

Towards Directive Explanations: Crafting Explainable AI Systems for Actionable Human-AI Interactions

Towards Directive Explanations: Crafting Explainable AI Systems for Actionable Human-AI Interactions

Can eXplainable AI Offer a New Perspective for Groundwater Recharge Estimation?—Global‐Scale Modeling Using Neural Network

Prediction of acoustic tinnitus suppression using resting state EEG: An explainable AI approach

Contact Info

Product

Resources

About