A*STAR Institute for Infocomm Research (A*STAR I²R)

A machine learning technique developed by A*STAR scientists could help patients with locked-in syndrome communicate via brain-machine interfaces.

High dynamic range imaging combined with deep learning approaches could improve the ability of autonomous vehicles to recognize traffic lights.

A*STAR researchers have developed a deep learning method to more accurately measure sleep duration and quality.

A new model called DECAPROP is helping machines to read more efficiently by enhancing their ability to understand the context of words.

A*STAR researchers have devised a machine learning technique to help antivirus developers stay ahead in the cat-and-mouse game of Android malware detection.

An A*STAR team has developed a ‘guard node’ approach to securing Internet of Things networks.

A*STAR scientists have designed sophisticated machine learning techniques that are more efficient at identifying anomalies in datasets.

New algorithm mines users’ most relevant reviews to better predict their tastes

New program picks out targets in a crowd quickly and efficiently

An algorithm gives robots an instinctive understanding of how to use tools

Using deep-learning techniques to locate potential human activities in videos

Scientists demonstrate the use of non-invasive brain recordings to ‘see through’ the cerebral cortex and characterize activity in deeper structures