A survey of explainable AI terminology

MA Clinciu, HF Hastie - 1st Workshop on Interactive Natural …, 2019 - research.ed.ac.uk
Abstract The field of Explainable Artificial Intelligence attempts to solve the problem of
algorithmic opacity. Many terms and notions have been introduced recently to define …

Understanding user intent modeling for conversational recommender systems: a systematic literature review

S Farshidi, K Rezaee, S Mazaheri, AH Rahimi… - User Modeling and User …, 2024 - Springer
User intent modeling in natural language processing deciphers user requests to allow for
personalized responses. The substantial volume of research (exceeding 13,000 …

Advancing cardiac diagnostics: Exceptional accuracy in abnormal ECG signal classification with cascading deep learning and explainability analysis

W Zeng, L Shan, C Yuan, S Du - Applied Soft Computing, 2024 - Elsevier
Arrhythmias, cardiac rhythm disorders, demand precise diagnosis for effective treatment
planning, emphasizing the crucial role of electrocardiogram (ECG) signal interpretation …

Artificial agents' explainability to support trust: considerations on timing and context

G Papagni, J de Pagter, S Zafari, M Filzmoser… - Ai & Society, 2023 - Springer
Strategies for improving the explainability of artificial agents are a key approach to support
the understandability of artificial agents' decision-making processes and their …

[BUCH][B] Adversarial Machine Learning: Attack Surfaces, Defence Mechanisms, Learning Theories in Artificial Intelligence

AS Chivukula, X Yang, B Liu, W Liu, W Zhou - 2023 - Springer
A significant robustness gap exists between machine intelligence and human perception
despite recent advances in deep learning. Deep learning is not provably secure. A critical …

Recurrence-aware long-term cognitive network for explainable pattern classification

G Nápoles, Y Salgueiro, I Grau… - IEEE transactions on …, 2022 - ieeexplore.ieee.org
Machine-learning solutions for pattern classification problems are nowadays widely
deployed in society and industry. However, the lack of transparency and accountability of …

ML-based performance modeling in SDN-enabled data center networks

B Nougnanke, Y Labit, M Bruyere… - … on Network and …, 2022 - ieeexplore.ieee.org
Traffic optimization and smart buffering are fundamental to achieve both great application
performance and resource efficiency in data centers with heterogeneous workloads …

Counterfactual explanation generation with minimal feature boundary

D You, S Niu, S Dong, H Yan, Z Chen, D Wu, L Shen… - Information …, 2023 - Elsevier
The complex and opaque decision-making process of machine learning models restrains
the interpretability of predictions and makes them cannot mine results outside of learning …

Learning hybrid interpretable models: Theory, taxonomy, and methods

J Ferry, G Laberge, U Aïvodji - arxiv preprint arxiv:2303.04437, 2023 - arxiv.org
A hybrid model involves the cooperation of an interpretable model and a complex black box.
At inference, any input of the hybrid model is assigned to either its interpretable or complex …

Integration of machine learning and statistical models for crash frequency modeling

D Zhou, VV Gayah, JS Wood - Transportation letters, 2023 - Taylor & Francis
Crash frequency modeling has been an active research topic in traffic safety, for which
various techniques have been proposed that can be loosely classified as either statistical …