Science

A new framework proposes treating data categories as a portfolio to improve accountability, mitigate risk, and enable transparent data allocation for artificial intelligence systems.

A new approach combines outlier control with directional illumination to reveal subtle trends in complex trajectory data.

A new framework utilizes generative models to create realistic synthetic attack data, bolstering defenses against increasingly sophisticated cyber intrusions.

New research demonstrates a method for improving the accuracy of automatically generated radiology reports by enabling AI to prioritize relevant anatomical regions within chest X-rays.

A new approach embeds the mechanisms of adaptation within neural networks, allowing them to dynamically control their own mutation and optimize for changing conditions.

A new large-scale dataset and training strategy are pushing the boundaries of what language models can achieve in complex mathematical problem-solving.

A new analysis reveals how fine-tuning machine learning algorithms dramatically improves their ability to detect and prevent network intrusions.

New research applies data mining techniques to uncover hidden thematic structures within the vast collection of Hadith literature.

New research reveals that the timing of mutation testing – whether before or after a model is pre-trained – significantly impacts the realism of synthetic faults generated in deep learning systems.

New research demonstrates a powerful machine learning technique for filtering out terrestrial interference, significantly enhancing the FAST telescope’s ability to detect potential signs of intelligent life.