Most of the time, robots grabbing the headlines boil down to a machine doing one very specific thing in a very controlled lab, followed by a promise that this somehow changes everything. Normally, I ...

Quick, predictable, and consistent activities provide a foundation to get students thinking and ready to learn.

Multi-task learning (MTL) represents a paradigm shift in the way machine learning models are developed, whereby multiple related tasks are learned simultaneously. By leveraging shared representations ...

Most robot headlines follow a familiar script: a machine masters one narrow trick in a controlled lab, then comes the bold promise that everything is about to change. I usually tune those stories out.

If that learning process is robust across a broad range of different tasks, then there's no reason why we shouldn't start seeing a new video like this every other day, as the 01 learns to do ...

Learning how a physical system behaves usually means repeating measurements and using statistics to uncover patterns. That approach works well in classical science. Once quantum effects dominate, the ...

Robot perception and cognition often rely on the integration of information from multiple sensory modalities, such as vision, ...