Chongfan Technology
News
25
2026
-
03
Optical Logic Convolutional Neural Network
Author:
A team led by Jianji Dong and Hailong Zhou at Huazhong University of Science and Technology has proposed the concept of an optical logic convolutional neural network (OLCNN). The authors demonstrate a 1×3 optical logic convolution operator (OLCO) for pattern generation and verify its high-speed computing capability of 20 Gbit/s. Subsequently, they implement a 2×2 OLCO to perform three types of image edge detection. By further scaling up, they construct a 3×3 OLCO for use in OLCNN and achieve four-class classification on the MNIST dataset, with an average test accuracy of 95.1%. By integrating optical logic devices with neural networks, this work pioneers a logic-driven paradigm for high-speed, energy-efficient optical hardware tailored for artificial intelligence.
The research findings were published in Science Advances on February 27, 2026, under the title “Optical logic convolutional neural network.”
Figure 1: Principle of OLCNN
Figure 2: Demonstration of a 1×3 optical logic convolution based on OLCO on the LNOI platform.
Figure 3: 2×2 OLCO demonstration based on the SOI platform
Figure 4: Optical logical convolution performed by a 2×2 OLCO
Figure 5: OLCNN based on 3×3 OLCO
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
