Researchers trained the tool, called FitRec, on a dataset of more than 250,000 workout records for more than 1,000 runners

With around 80,000 untested chemicals in use, Rutgers-led innovation addresses an urgent environmental safety need

Training a deep learning network involves breaking a data sample into chunks of consecutive data points

Traditional surveillance cameras do not always detect suspicious activities or objects in a timely manner

A new study finds that humans can think like computers

"Chronoprints" can identify a sample from a video taken as it reacts to disturbance

The new technology, called Pattern to Knowledge (P2K), can predict the binding of biosequences in seconds

Researchers report machine learning speeds discovery of new materials

Deep neural networks to detect magnetic field anomalies for faster warnings before earthquakes and tsunamis

CAMERA researchers develop highly efficient neural networks for analyzing experimental scientific images from limited training data