Add BrightSurf on Google Email

Search results for “Aeronautics”

642 results for "Aeronautics"

Algorithm helps artificial intelligence systems dodge "adversarial" inputs

A new deep-learning algorithm, CARRL, is designed to help machines build a healthy skepticism of their measurements and inputs. By combining reinforcement-learning algorithms with deep neural networks, researchers created an approach that outperformed standard machine-learning techniques in scenarios with uncertain and adversarial inputs.

SourceMassachusetts Institute of Technology·JournalIEEE Transactions on Neural Networks and Learning Systems·DateMar 7, 2021

Greenland ice losses rising faster than expected

The Greenland ice sheet has lost 3.8 trillion tonnes of ice since 1992, with the rate of ice loss increasing seven-fold over three decades. The study's findings show that the ice sheet is tracking the IPCC's high-end climate warming scenario, predicting 40 million people will be exposed to coastal flooding by 2100.

SourceUniversity of Leeds·JournalNature·DateDec 10, 2019

Supercomputers use graphics processors to solve longstanding turbulence question

Researchers at Imperial College London used supercomputers and graphics processors to simulate turbulent fluid flow and solve a longstanding question about disturbance dissipation. Their results lead to the development of new empirical models for turbulence, improving engineering designs in fields like wind turbines and Formula 1 cars.

SourceImperial College London·JournalJournal of Fluid Mechanics·DateJul 25, 2019

Spotting objects amid clutter

Researchers at MIT develop a new algorithm that can accurately pick out an object, such as a small animal, in a dense cloud of dots within seconds. The technique prunes away outliers quickly, even for increasingly dense clouds, making it suitable for applications like driverless cars and robotic assistants.

Blast to the future

Researchers at Argonne National Laboratory are developing a machine learning-based framework called BLAST to accelerate and simplify materials modeling and simulation. This software will enable companies to quickly perform molecular dynamics simulations needed for new material vetting, with applications in polymers and steel alloys.