
Chinese scientists have developed a reconfigurable integrated photonic chip capable of running diverse neural networks, including those for image and speech processing, with high efficiency.
Key Details
- 1The chip integrates microring resonators and Mach-Zehnder interferometers, powered by a soliton microcomb light source.
- 2Supports fully-connected, convolutional, and recurrent neural networks within a single hardware architecture.
- 3Area efficiency reaches up to 2.45 TOPS/mm² at 10 GHz frequency.
- 4Demonstrated on tasks: image classification (MNIST 92.93% accuracy, CIFAR-10 56.57%), sentiment analysis (IMDB 80.81%), and speech recognition.
- 5Device enables dual-path computation per resonator, doubling throughput versus traditional schemes.
Why It Matters

Source
EurekAlert
Related News

Chinese Researchers Unveil Photonic Chip for Ultra-Fast Image Processing
A new photonic chip achieves image processing at 25 million frames per second with high energy efficiency, promising major advances in real-time imaging and AI applications.

AI Model Predicts Growth Spurts from Pediatric Neck X-rays for Orthodontics
Korean researchers developed an AI system (ARNet-v2) that predicts children's growth spurts from neck X-rays to enhance orthodontic treatment planning.

Dana-Farber Showcases AI and Clinical Trial Advances at ESMO 2025
Dana-Farber researchers present major cancer clinical trial results, including AI-driven data analysis, at ESMO Congress 2025.