Chongfan Technology
News
06
2026
-
08
Parallel Nonlinear Neuromorphic Computing Based on Spatiotemporal Metasurfaces
Author:
The teams of Hongsheng Chen and Chao Qian at Zhejiang University have proposed a parallel nonlinear neuromorphic processor that, by leveraging only the temporal encoding of spatiotemporal metasurfaces, enables arbitrary superpositions of information states across multidimensional channels. The authors experimentally validated their design using distributed spatiotemporal metasurfaces, demonstrating robust performance in multi‑label classification and asynchronous‑modulated multitask parallel processing. Furthermore, their nonlinear processor exhibits dynamic memory capabilities in real‑time responses to a prototypical maze‑solving task. This work paves a flexible pathway for developing diverse time‑modulated neuromorphic processors tailored to complex scenarios.
The research findings were published in Science Advances on July 29, 2026, under the title “Parallel nonlinear neuromorphic computing with temporal encoding.”
Figure 1: A parallel nonlinear metasurface processor with temporal encoding
Figure 2: Time‑nonlinear neural network mechanism based on a distributed spatiotemporal metasurface
Figure 3: Multi-tag recognition task based on a nonlinear metasurface processor
Figure 4: Demonstration of residual convolution operations and scalability in a nonlinear metasurface processor.
Figure 5: Nonlinear multitask demonstration with asynchronous modulation
Figure 6: Solving a maze problem using a nonlinear metasurface agent.
Source: Optics World
LATEST NEWS
Thank you for visiting the official website of Chongfan Technology. If you have cooperation intentions or suggestions, please contact us through the following methods, and we will reply as soon as possible, thank you!
Address: Room 403, Building 6, Phase III of R&D, No. 36 Xiyong Avenue, High tech Zone, Chongqing, China.
Telephone: +86-13658337211
E-mail: Sales@cfkeji.net
Website: www.cfkeji.net
Mobile Version
