Scalable multilayer diffractive neural network with all-optical nonlinear activation

2025/04/18 by Dong, Yiying, Zhang, Bohan, Liang, Ruiqi +7
#FOS: Physical sciences #Optics (physics.optics)

paper · doi:10.48550/arxiv.2504.13518

Abstract

All-optical diffractive neural networks (DNNs) offer a promising alternative to electronics-based neural network processing due to their low latency, high throughput, and inherent spatial parallelism. However, the lack of reconfigurability and nonlinearity limits existing all-optical DNNs to handling only simple tasks. In this study, we present a folded optical system that enables a multilayer reconfigurable DNN using a single spatial light modulator. This platform not only enables dynamic weight reconfiguration for diverse classification challenges but crucially integrates a mirror-coated silicon substrate exhibiting instantaneous \chi(3) nonlinearity. The incorporation of all-optical nonlinear activation yields substantial accuracy improvements across benchmark tasks, with performance gains becoming increasingly significant as both network depth and task complexity escalate. Our system represents a critical advancement toward realizing scalable all-optical neural networks with complex architectures, potentially achieving computational capabilities that rival their electronic counterparts while maintaining photonic advantages.

Citations

• Training Hybrid Neural Networks with Multimode Optical Nonlinearities Using Digital Twins
• The physics of optical computing
• Nonlinear Processing with Linear Optics
• Semiconductor quantum dots: Technological progress and future challenges
• An optical neural network using less than 1 photon per multiplication
• Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems
• Free-space optical neural network based on thermal atomic nonlinearity
• Parallel convolution processing using an integrated photonic tensor core
• 11 TeraFLOPs per second photonic convolutional accelerator for deep learning optical neural networks
• Scaling Laws for Autoregressive Generative Modeling
• Massively Parallel Amplitude-Only Fourier Neural Network
• Scaling Laws for Neural Language Models
• All-optical spiking neurosynaptic networks with self-learning capabilities
• All Optical Neural Network with Nonlinear Activation Functions
• All-Optical Machine Learning Using Diffractive Deep Neural Networks
• Neuromorphic Silicon Photonic Networks
• Deep Learning with Coherent Nanophotonic Circuits

Related

• Multi-Dimensional Reconfigurable, Physically Composable Hybrid Diffractive Optical Neural Network
• All-Optical Machine Learning Using Diffractive Deep Neural Networks
• All Optical Classification Surpasses Cascaded Diffractive Networks through Dual Wavelength Differential Modulation within a Single Layer Architecture
• A surface-normal photodetector as nonlinear activation function in diffractive optical neural networks
• Scalability of On-chip Diffractive Optical Neural Networks