Science

A new study challenges the assumption that powerful foundation models automatically translate to improved performance in financial risk assessment.

Understanding the complex network of components and actors behind artificial intelligence is becoming crucial for safe and reliable deployment in critical systems.

A new framework leverages federated learning and interpretable neural networks to bolster resilience in power transmission networks.

Researchers have developed a new framework that combines machine learning with large language models to improve predictions of patient outcomes and inform more effective, affordable care.

Researchers have developed a deep learning framework, IonCast, to improve the accuracy of global ionospheric forecasting and enhance our understanding of space weather events.

New research demonstrates how combining market sentiment analysis with advanced time series modeling can improve forecasting accuracy for the volatile semiconductor industry.

New deep learning techniques are dramatically improving our ability to identify and classify these powerful, but fleeting, astronomical events.

New research reveals that attempts to remove identifying information from financial text data, while intended to prevent bias, ironically diminish the reliability of insights extracted by advanced language models.

Researchers are applying rigorous mathematical analysis to understand and reduce the tendency of large language models to generate factually incorrect or nonsensical content.

A new approach to reservoir computing leverages random Fourier features to more accurately forecast systems with interacting fast and slow processes.