A sweeping new survey in Vicinagearth maps the algorithms, applications, and open challenges of transfer metric learning, the technique that...

Researchers in India have built a custom fine-tuned BERT-based framework that outperforms classical machine learning, deep learning baselines, and GPT-3.5...

Brazilian researchers have used a deep metric learning technique called N-pair loss to retrieve visually similar rock tomography images with...

An AI-driven inverse design protocol combining a Hammett-encoded neural network with genetic and swarm optimization has uncovered singlet fission candidates...

A large-scale study from the University of São Paulo tested three strategies for detecting outliers in categorical and mixed data...

A semi-automated AI segmentation framework converts routine cervical spine MRI into quantitative measures of disc degeneration that correspond with standard...

Researchers trained a convolutional neural network to detect and characterize eating disorder discourse on Weibo, uncovering five major themes in...

A new fairness-regularized framework called CoR-Hate retrieves real counterfactual examples from corpus data to reduce identity bias in hate-speech detection...

Researchers have developed a compact optimized convolutional neural network framework that classifies multiple lung diseases from CT and chest X-ray...

Researchers have built a five-branch hybrid deep learning framework called ADAPT-FUSE that predicts cross-border e-commerce delivery delays with competitive accuracy...