Convolutional optical neural networks herald a new era for AI imaging
Who led the CNNs into optics research?
The research team led by Prof. Min Gu and Prof. Qiming Zhang from the School of Artificial Intelligence Science and Technology (SAIST) at the University of Shanghai for Science and Technology (USST) successfully introduced the concept of CNNs into the field of optics and realized a convolutional all-optical neural network2.
How do convolutional ONNs improve imaging speed?
Convolutional optical neural networks (ONNs) improve imaging speed by performing convolution network operations directly in the optical domain, eliminating the need for signal conversion between electronic and optical signals. This allows for true optical computing speeds and enables the use of multiple parallel cores capable of operating at the speed of light, directly extracting features from scattered light for rapid image reconstruction.
What are convolutional optical neural networks?
Convolutional optical neural networks (ONNs) are a type of artificial neural network that use optical components to perform computations. They are inspired by convolutional neural networks (CNNs), which excel in image recognition tasks. ONNs offer the potential for faster and more energy-efficient computations by leveraging the parallel processing capabilities of light. They have applications in areas such as autonomous driving, robotic vision, and medical imaging.