The method enables a model to determine its confidence in a prediction, while using no additional data and far fewer computing resources than other methods.

A new measure can help scientists decide which estimation method to use when modeling a particular data problem.

Computer scientists want to know the exact limits in our ability to clean up, and reconstruct, partly blurred images.

But the harm from a discriminatory AI system can be minimized if the advice it delivers is properly framed, an MIT team has shown.

This year's fellows will work across research areas including telemonitoring, human-computer interactions, operations research,  AI-mediated socialization, and chemical transformations.

New research enables users to search for information without revealing their queries, based on a method that is 30 times faster than comparable prior techniques.

Researchers used a powerful deep-learning model to extract important data from electronic health records that could assist with personalized medicine.

New technique significantly reduces training and inference time on extensive datasets to keep pace with fast-moving data in finance, social networks, and fraud detection in cryptocurrency.

New technique could diminish errors that hamper the performance of super-fast analog optical neural networks.

New research reveals a scalable technique that uses synthetic data to improve the accuracy of AI models that recognize images.