Spatially Parallel All-optical Neural Networks
This work addresses signal degradation and nonlinearity limitations in all-optical neural networks, offering a scalable strategy for ultrafast and energy-efficient optical computing, though it appears incremental as it builds on existing AONN paradigms.
The authors tackled the problem of signal degradation and limited nonlinearity in all-optical neural networks by proposing a spatially parallel architecture, which improved accuracy, noise robustness, and expressivity in image classification benchmarks as the number of parallel sub-networks increased.
All-optical neural networks (AONNs) have emerged as a promising paradigm for ultrafast and energy-efficient computation. These networks typically consist of multiple serially connected layers between input and output layers--a configuration we term spatially series AONNs, with deep neural networks (DNNs) being the most prominent examples. However, such series architectures suffer from progressive signal degradation during information propagation and critically require additional nonlinearity designs to model complex relationships effectively. Here we propose a spatially parallel architecture for all-optical neural networks (SP-AONNs). Unlike series architecture that sequentially processes information through consecutively connected optical layers, SP-AONNs divide the input signal into identical copies fed simultaneously into separate optical layers. Through coherent interference between these parallel linear sub-networks, SP-AONNs inherently enable nonlinear computation without relying on active nonlinear components or iterative updates. We implemented a modular 4F optical system for SP-AONNs and evaluated its performance across multiple image classification benchmarks. Experimental results demonstrate that increasing the number of parallel sub-networks consistently enhances accuracy, improves noise robustness, and expands model expressivity. Our findings highlight spatial parallelism as a practical and scalable strategy for advancing the capabilities of optical neural computing.