Computer Sciences

Using adversarial attacks to refine molecular energy predictions

Neural networks (NNs) are increasingly being used to predict new materials, the rate and yield of chemical reactions, and drug-target interactions, among others. For these applications, they are orders of magnitude faster ...

Robotics

These robots can move your couch

To train robots how to work independently but cooperatively, researchers at the University of Cincinnati gave them a relatable task: Move a couch.

Computer Sciences

New simulator helps robots sharpen their cutting skills

Researchers from the University of Southern California (USC) Department of Computer Science and NVIDIA have unveiled a new simulator for robotic cutting that can accurately reproduce the forces acting on a knife as it slices ...

Robotics

Neuro-evolutionary robotics: A gap between simulation and reality

Neuro-evolutionary robotics is an attractive approach to realize collective behaviors for swarms of robots. Despite the large number of studies that have been devoted to it and although many methods and ideas have been proposed, ...

Electronics & Semiconductors

AI may soon predict how electronics fail

Think of them as master Lego builders, only at an atomic scale. Engineers at CU Boulder have taken a major step forward in combing advanced computer simulations with artificial intelligence to try to predict how electronics, ...

Robotics

Bird-like wings could help drones keep stable in gusts

Wings that can vary their shapes as freely as birds' wings could have advantages for small aircraft in built environments, a new study led by engineers at the University of Michigan suggests.

Computer Sciences

Trust the machine—it knows what it is doing

Machine learning, when used in climate science builds an actual understanding of the climate system, according to a study published in the journal Chaos by Manuel Santos Gutiérrez and Valerio Lucarini, University of Reading, ...

Engineering

Eco-friendly device detects real-time pipe damage

A researcher at University of Limerick has developed a low-cost, environmentally friendly sensor that can detect damage in pipelines and could save water as a result.

page 9 from 27