We design a silicon-based optical neural network (ONN) chip based on coherent detection. Nonnegative neural networks are trained and tested on three different datasets and test accuracies are 96.67%, 97.22% and 96.16% respectively.Ruiting Wang...
A classical fully connected neural network has been experimentally demonstrated on an integrated silicon photonic chip29,30. Although this optical chip is based on light interference, the implemented neural network algorithms are real-valued, which forfeits the benefits of complex-valued neural networks...
Optical neural networks are considered next-generation physical implementations of artificial neural networks, but their capabilities are limited by on-chip integration scale and requirement for coherent light sources. This study proposes a spectral convolutional neural network (SCNN) with matter meta-imagin...
An on-chip photonic deep neural network for image classification. Nature 606, 501–506 (2022). Article ADS Google Scholar Bernstein, L. et al. Single-shot optical neural network. Sci. Adv. 9, eadg7904 (2023). Article Google Scholar Liu, Z. et al. Efficient and robust LiDAR-based ...
Melloni stated, “The advantages of photonic neural networks have long been known, but one of the missing pieces to fully exploit their potential was network training. It is like having a powerful calculator, but not knowing how to use it. In this study, we succeeded in implementing training...
In the future, using sound waves for optical neural networks could unlock a new class of optical neuromorphic computing which could be reconfigured spontaneously and would allow large-scale in-memory computing in the present telecommunication network. Also, on-chip implementations of optical neura...
PCMs are commonly used with DVDs or Blu-ray Discs as optical data storage elements. “PCMs as nonvolatile memory elements have the additional advantage that no energy is needed to keep their phase-state, meaning that in the case of the trained neural network with fixed weights,” Feldmann sai...
The paper used a network based on the same code as KSH's network - that is, just the type of network that is being increasingly widely used. While such neural networks compute functions which are, in principle, continuous, results like this suggest that in practice they're likely to ...
Concept of photonic chip based on ultrafast laser-induced phase change.aSchematic diagram of photonic chips.bRepresentative architecture of multilayer neural networks.cSchematics of photonic convolutional network based on Sb film. The purple blocks illustrate PCM Sb film.dIllustration of crystalline structu...
Single-chip photonic deep neural network with forward-only training Article02 December 2024 Training large-scale optoelectronic neural networks with dual-neuron optical-artificial learning ArticleOpen access04 November 2023 Main The rapid advancement of machine learning is transforming the sciences and techno...