Researchers have proposed and demonstrated a new computational imaging method by the incorporation of a physical model into a deep neural network, according to a recent research article published in the journal Light: Science and Applications.
Deep neural networks have been widely used in computational imaging, but most of them need a large amount of labeled data to train.
Depending on the network architecture and amount of data used for training, the network training process can take several hours or even several days, said the article.
In the article, the researchers from the Chinese Academy of Sciences, the University of Stuttgart and the Massachusetts Institute of Technology proposed a widely applicable physics-enhanced deep neural network, or PhysenNet for short, without the requirement of training data.
They demonstrated the applicability of PhysenNet in phase imaging. When a single diffraction image was fed into a PhysenNet model, the network weight and bias factors will be optimized through the interplay between the neural network and the physical model.
The new method opens up a new paradigm for the design and use of artificial intelligence in computational imaging. (Xinhua)
Property developer Evergrande Group has signed contracts with the Chinese Academy of Sciences (CAS) to develop cutting-edge technologies in a bid to renovate its businesses. According to a deal signed Thursday, the two parties will jointly develop six projects including supercomputing, artificial intelligence, and surgical robots.
As China's population declines, experts are calling for more research into artificial intelligence, big data and smart manufacturing to maintain an economic and industrial edge and to drive development. China's rapid development means it's no longer unusual to see fixed robot arms working around the clock, performing simple, highly repetitive tasks, such as welding and moving components on a typical production line.
86-10-68597521 (day)
86-10-68597289 (night)
86-10-68511095 (day)
86-10-68512458 (night)
cas_en@cas.cn
52 Sanlihe Rd., Xicheng District,
Beijing, China (100864)
Copyright © 2002 - Chinese Academy of Sciences
