Computer Sciences

Large sequence models for sequential decision-making

Transformer architectures have facilitated the development of large-scale and general-purpose sequence models for prediction tasks in natural language processing and computer vision, for example, GPT-3 and Swin Transformer.

Computer Sciences

Evolutionary computation for expensive optimization: A survey

The term 'Expensive optimization problem' (EOP) refers to any problem that requires expensive or even unaffordable costs to evaluate candidate solutions. These problems exist in many significant real-world applications.

Engineering

New wind field models accurately describe wind gusts

Researchers at the University of Oldenburg, Germany, have developed a new statistical model with which they can describe wind turbulence with considerably greater accuracy than ever before. The team of scientists from the ...

page 1 from 2