Tag: Machine learning

Researchers have introduced Neural Probabilistic Circuits, an AI architecture that pairs neural attribute recognition with probabilistic circuits to deliver image ...

Researchers at IIT Jodhpur have built a retrieval-augmented AI framework and a massive new dataset, FactViz3M, that can locate the ...

A hybrid machine learning framework that reads leaf color, texture, and vein patterns diagnosed magnesium and iron deficiencies in field-grown ...

Researchers used an explainable machine learning model built from 216 diverse VEGFR-2 inhibitors to discover a novel naphthalene-substituted phthalazine compound ...

A year-long dual-laboratory study of 51 healthy donors shows that immunoglobulin subclass levels are remarkably stable within individuals yet vary ...

Researchers have created a hybrid onboard model for turboshaft engines that combines component-level physics simulations with sparse flight data calibration, ...

A new phased client selection method for federated learning improves accuracy, cuts training time and communication costs, and strengthens defenses ...

A new graph neural network study of spatial transcriptomics finds that attention mechanisms, not elaborate edge features, drive accurate identification ...

A study of nearly 12,000 patients found that leading large language models matched or exceeded an intermediate ophthalmologist in recommending ...

A systematic review of 207 studies finds that machine learning models, especially convolutional neural networks and random forests, consistently beat ...