Tag: Explainable AI

A new study shows deep learning EEG classifiers gain inflated accuracy from visual instruction cues rather than genuine motor imagery ...

Researchers have built SpudNet5-R3, a lightweight explainable convolutional neural network that detects potato early and late blight with up to ...

A new review examines how artificial intelligence and machine learning could transform the design of sustainable, non-toxic marine antifouling coatings ...

A unified explainable AI framework applied to Chicago, Los Angeles, and New York City shows XGBoost best detects crime hotspots ...

Researchers have developed X-URL, a character-level deep learning framework that classifies malicious URLs into four threat categories with over 98 ...

A new neuro-symbolic framework called Delta Semantics keeps machine learning outputs provably consistent with evolving ontologies by attaching checker-validated proof ...

An Indian research team has developed GraphX, an explainable graph transformer framework that classifies nail diseases with 94.97 percent accuracy ...

Researchers have built a reuse-aware, package-level fault prediction model for Java applications that pairs architectural metrics with SHAP and LIME ...

Researchers at the University of Calabria have developed RLAX, a reinforcement learning framework that identifies compact, interpretable feature subspaces explaining ...

A new framework called FLARE combines nonlinear machine learning flexibility with closed-form uncertainty estimates, statistical tests, and patient-level interaction analysis ...

Researchers have unveiled an explainable deep learning framework that detects insect crop pests in real time with up to 98 ...

Researchers in India combined µEDM drilling experiments on titanium with benchmarked machine learning models, explainable AI, and a surrogate-based inverse ...

Researchers have developed a hierarchical temporal graph network that predicts student academic outcomes with high accuracy while using gradient-based attribution ...

A new risk-calibrated tabular Transformer achieves state-of-the-art Alzheimer's disease staging while calibrating its confidence and abstaining on uncertain cases.

Researchers have built an explainable stacked ensemble of boosting algorithms that predicts Bitcoin's short-term closing prices with 97.5 percent explained ...

Researchers have built a hybrid transformer-U-Net that segments diabetic foot ulcers with expert-level overlap and quantitatively explainable visualisations.

A new benchmark study shows that data augmentation lifts pre-trained deep learning models to up to 98.06% accuracy in classifying ...

Researchers used explainable AI to fingerprint the internal layers responsible for safety alignment in open-source large language models and showed ...

Researchers trained an explainable XGBoost model on 1,670 field-recorded concrete mixes, achieving R-squared 0.9263 in strength prediction while using SHAP ...

Researchers in India have built a hybrid graph neural network framework that converts retinal images into graph structures, achieving up ...