Smart Nation and Digital Economy (SNDE)

A new data selector helps more accurately train machine learning algorithms by recycling datasets from other applications.

A systematic comparison of different existing methods reveals best practices for anomaly detection and diagnosis in cyber-physical systems.

An innovation from A*STAR material scientists does the job of multiple sensor devices through its ability to change detection targets.

Scientists are creating advanced nanopatterned metasurfaces for projecting high-resolution 3D holograms in augmented reality headsets, thereby making the user experience more immersive.

A new method to create artificial synapses developed by A*STAR researchers could make neural networks more efficient and less energy-intensive.

In developing a new process to synthesise stable qubits, A*STAR researchers are paving the way toward scalable and practical quantum devices.

Obviating the need for large datasets in machine translation models could be a reality, thanks to a new method for diversifying training data

A new mathematical model quickly and reliably predicts the origin of disruptive electromagnetic interference emanating from complex electronic circuits.

By linking past observations with future possibilities, a novel framework could help computers predict human actions more accurately.

Revealing how abnormalities form and grow in piezoelectric films could make smart devices better at making the right connections.

A novel machine learning framework makes it faster and easier to train robots that can perform tasks with unprecedented precision.

A*STAR’s steady investments in R&D and talent create the ideal conditions for impactful science, says its Chief Executive Officer Frederick Chew.