A method to interpret artificial intelligence (AI) models used in materials discovery by analyzing their learned features has been developed by researchers from Japan. The method extracts key features ...

A new single-protein analysis technique gives researchers an unprecedented ability to study proteins called scramblases, which have critical roles in biology. The development of the new technique, in ...

Researchers developed a hybrid UMAP-HDBSCAN-SVM machine learning workflow to rapidly classify low-loss STEM-EELS spectrum ...

Penn Engineers have developed an open-source algorithm that combines the speed of AI with the precision of geometry to ...

Understanding how neural circuit activity emerges from, and feeds back into, underlying molecular states is a central challenge in modern neuroscience.