Bidirectional Optical Neural Networks Based on Free-Space Optics Using Lens Arrays and Spatial Light Modulator

• Published in: Micromachines (Basel) Vol. 15; no. 6; p. 701
• Main Author: Ju, Young-Gu
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 25.05.2024; MDPI
• Subjects: Algorithms; Arrays; Artificial neural networks; Back propagation; Back propagation networks; backpropagation; Clustering; Free space optics; Hardware; lens array; Light; Machine learning; Multilayers; neural network; Neural networks; optical computer; optical neural network; Optical properties; Optical wireless; Optics; Photodiodes; Semiconductor lasers; Spatial light modulators; Supervised learning; Germany; optical neural network; free-space optics; optical computer; neural network; backpropagation; lens array
• ISSN: 2072-666X; 2072-666X
• DOI: 10.3390/mi15060701

This paper introduces a novel architecture-bidirectional optical neural network (BONN)-for providing backward connections alongside forward connections in artificial neural networks (ANNs). BONN incorporates laser diodes and photodiodes and exploits the properties of Köhler illumination to establish optical channels for backward directions. Thus, it has bidirectional functionality that is crucial for algorithms such as the backpropagation algorithm. BONN has a scaling limit of 96 × 96 for input and output arrays, and a throughput of 8.5 × 10 MAC/s. While BONN's throughput may rise with additional layers for continuous input, limitations emerge in the backpropagation algorithm, as its throughput does not scale with layer count. The successful BONN-based implementation of the backpropagation algorithm requires the development of a fast spatial light modulator to accommodate frequent data flow changes. A two-mirror-like BONN and its cascaded extension are alternatives for multilayer emulation, and they help save hardware space and increase the parallel throughput for inference. An investigation into the application of the clustering technique to BONN revealed its potential to help overcome scaling limits and to provide full interconnections for backward directions between doubled input and output ports. BONN's bidirectional nature holds promise for enhancing supervised learning in ANNs and increasing hardware compactness.