<p>➀ Researchers developed a silicon photonic chip using light for AI computations, reducing energy consumption by up to 100 times; </p><p>➁ The chip integrates ultrathin Fresnel lenses for optical convolution, achieving 98% accuracy in tasks like handwritten digit recognition; </p><p>➂ Supports wavelength multiplexing for parallel processing, offering potential for sustainable AI scaling and industry adoption.</p>
Related Articles
- Advanced Motion Sensing For Smart Glassesabout 1 month ago
- Qualcomm adds UHF RFID to mobile processor2 months ago
- Ed Goes For Humanoid Robots3 months ago
- Building Future-Ready AI Hardware With Neuromorphic Computing And Sensing3 months ago
- System On Module For Edge AI5 months ago
- VSORA raises $46m for inference IC6 months ago
- Ed Gets Into Humanoid Robots6 months ago
- Symposium on VLSI Technology & Circuits in Kyoto,6 months ago
- Prototype of a Particularly Sustainable and Energy-Autonomous E-Bike Terminal Developed at HKA7 months ago
- Smart and Compact Sensors with Edge-AI7 months ago