[HTML][HTML] Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence
Artificial intelligence (AI) is currently being utilized in a wide range of sophisticated
applications, but the outcomes of many AI models are challenging to comprehend and trust …
applications, but the outcomes of many AI models are challenging to comprehend and trust …
An ensemble machine learning framework for Airbnb rental price modeling without using amenity-driven features
Purpose The prediction of Airbnb listing prices predominantly uses a set of amenity-driven
features. Choosing an appropriate set of features from thousands of available amenity …
features. Choosing an appropriate set of features from thousands of available amenity …
Xrl-shap-cache: an explainable reinforcement learning approach for intelligent edge service caching in content delivery networks
Content delivery networks (CDNs) play a pivotal role in the modern internet infrastructure by
enabling efficient content delivery across diverse geographical regions. As an essential …
enabling efficient content delivery across diverse geographical regions. As an essential …
Unveiling sar target recognition networks: Adaptive perturbation interpretation for enhanced understanding
Deep neural networks (DNNs) have obtained remarkable achievements in various vision
tasks. However, DNNs' mechanism remains obscure, especially in synthetic aperture radar …
tasks. However, DNNs' mechanism remains obscure, especially in synthetic aperture radar …
Analytical interpretation of the gap of CNN's cognition between SAR and optical target recognition
Synthetic aperture radar (SAR) automatic target recognition (ATR) is a crucial technique
utilized in various scenarios of geoscience and remote sensing. Despite the remarkable …
utilized in various scenarios of geoscience and remote sensing. Despite the remarkable …
Towards effective human-ai decision-making: The role of human learning in appropriate reliance on ai advice
The true potential of human-AI collaboration lies in exploiting the complementary
capabilities of humans and AI to achieve a joint performance superior to that of the individual …
capabilities of humans and AI to achieve a joint performance superior to that of the individual …
Review on the use of AI-based methods and tools for treating mental conditions and mental rehabilitation
This review provides a thorough examination of recent developments in artificial intelligence
analysis methods within mental and psychiatry field. By analyzing and comparing results …
analysis methods within mental and psychiatry field. By analyzing and comparing results …
A singular Riemannian geometry approach to deep neural networks II. Reconstruction of 1-D equivalence classes
We proposed in a previous work a geometric framework to study a deep neural network,
seen as sequence of maps between manifolds, employing singular Riemannian geometry …
seen as sequence of maps between manifolds, employing singular Riemannian geometry …
XAIRF-WFP: a novel XAI-based random forest classifier for advanced email spam detection
Spam detection is a critical cybersecurity and information management task with significant
implications for security decision-making processes. Traditional machine learning …
implications for security decision-making processes. Traditional machine learning …
CausalCOMRL: Context-Based Offline Meta-Reinforcement Learning with Causal Representation
Z Zhang, W Meng, H Sun, G Pan - arxiv preprint arxiv:2502.00983, 2025 - arxiv.org
Context-based offline meta-reinforcement learning (OMRL) methods have achieved
appealing success by leveraging pre-collected offline datasets to develop task …
appealing success by leveraging pre-collected offline datasets to develop task …