Tag: neural networks

Researchers at TU Delft have developed MonoRace, an AI system that flew a racing drone at up to 100 km/h ...

An AI decision-support model tested across 85 automotive, electronics, and textile plants achieved up to 27 percent lower energy use, ...

Researchers in Switzerland have developed an uncertainty-weighted neural network that incorporates standardized measurement uncertainty into both training and evaluation, improving ...

Researchers at Durham University have developed a dual-stream neural network that applies parallel attention to sensor modalities and time steps, ...

A new framework called TAL-CGBR improves temporal action localization by feeding classification semantics into boundary regression, achieving 68.5 percent average ...

Researchers in Chengdu have developed a predefined-time adaptive neural backstepping controller that forces electro-hydraulic actuators to converge within designer-set deadlines ...

Researchers in China have improved facial expression recognition by redesigning how a ConvNeXt network downsamples images and integrates spatial-channel attention, ...

Researchers have developed MAPLE, a black-box adversarial defense framework that jointly purifies adversarial images and recalibrates the classifier's decision margins ...

A neutrosophic neural network approach developed for wafer fabrication can identify which AI-generated factory due dates are unreliable, finding that ...

Researchers at Jilin University have developed a Kolmogorov-Arnold network-based inverse mapping model that identifies groundwater contamination sources within seconds, achieving ...