Machine learning

A new approach combines surface-enhanced Raman spectroscopy with advanced computer analysis to accurately and rapidly detect lung cancer by analysing fluid around the lungs.

A new deep learning method outperforms traditional methods for identifying genetic mutations from DNA sequences and can be a valuable tool for improved cancer diagnostics.

A pioneering computational framework empowers robots to acquire, recognise and effectively use previously unseen tools.

Researchers teach artificial intelligence systems how to process information by mimicking human introspection.

Unique gene signatures associated with drug-resistant leukaemia paves the way for improved clinical strategies to help these patients.

A new machine learning platform offers more accurate traffic predictions for safer, less congested roads.

A new automated video summarisation model uses viewers’ brain signals to extract reel highlights that evoke emotions.

A novel machine learning model predicts wear and tear in manufacturing parts with less real-world data for cost savings and improved productivity.

A new high-efficiency computational technique identifies optimal combinations of metals for stable alloys, fast-tracking the discovery process for materials engineers.

A new framework gives pre-trained machine learning models the ability to perform optimally in real-world settings, even with limited training data.

By analysing heart cells, a new machine learning algorithm could help predict arrhythmia risk before symptoms appear.

Technology for finding non-visual defects in semiconductors leaps forward thanks to an online machine learning algorithm that learns on the fly.