Tag: deep learning

A patent-pending SUNY invention pairs time-domain and frequency-domain signal representations with a cosine similarity loss function to improve detection of ...

Researchers have developed a deep learning framework that generates anatomically accurate synthetic aortic geometries with realistic calcifications, enabling large virtual ...

Researchers have developed a frequency-domain AI network that detects periodic patterns in human check-in data to predict a user's next ...

A new AI retrosynthesis system called RetroChimera combines models with complementary inductive biases to outperform leading baselines and earn the ...

Researchers have developed OphthUS-GPT, a multimodal AI system that automatically generates and interprets diagnostic reports from ophthalmic B-scan ultrasound images ...

NanoTS, a new deep learning tool published in Nature Methods, enables accurate SNP detection and genotype calling from nanopore long-read ...

A new adaptive multi-task neural network called AXMLN dramatically improves radio signal detection at extremely low signal-to-noise ratios, providing a ...

Researchers combined scanning electron microscopy with a deep learning framework to automatically classify salt-weathering deterioration in granite, achieving up to ...

Researchers in Morocco have developed IACAN, a deep learning architecture that dynamically balances convolutional and attention branches using KL divergence ...

Researchers have developed a graph-enhanced bidirectional GRU model that detected 44 of 45 simulated anomalies in a realistic power generation ...