2023/08/28 by Brandon Redding, Redding, Brandon, Joseph B. Murray +9 · 2 citations
Computer Science · Engineering · Physics and Astronomy · #Emerging Technologies (cs.ET) #FOS: Computer and information sciences #FOS: Physical sciences #Neural Networks and Reservoir Computing #Optical Network Technologies #Optics (physics.optics) #Random lasers and scattering media
paper · pdf · doi:10.48550/arxiv.2308.14504
openalex publication_date 2023/08/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The widespread adoption of machine learning and other matrix intensive computing algorithms has inspired renewed interest in analog optical computing, which has the potential to perform large-scale matrix multiplications with superior energy scaling and lower latency than digital electronics. However, most existing optical techniques rely on spatial multiplexing to encode and process data in parallel, requiring a large number of high-speed modulators and detectors. More importantly, most of these architectures are restricted to performing a single kernel convolution operation per layer. Here, we introduce a fiber-optic computing architecture based on temporal multiplexing and distributed feedback that performs multiple convolutions on the input data in a single layer (i.e. grouped convolutions). Our approach relies on temporally encoding the input data as an optical pulse train and injecting it into an optical fiber where partial reflectors create a series of delayed copies of the input vector. In this work, we used Rayleigh backscattering in standard single mode fiber as the partial reflectors to encode a series of random kernel transforms. We show that this technique effectively performs a random non-linear projection of the input data into a higher dimensional space which can facilitate a variety of computing tasks, including non-linear principal component analysis, support vector machines, or extreme learning machines. By using a passive fiber to perform the kernel transforms, this approach enables efficient energy scaling with orders of magnitude lower power consumption than GPUs, while using a high-speed modulator and detector maintains low latency and high data-throughput. Finally, our approach is readily integrated with fiber-optic communication links, enabling additional applications such as processing remote sensing data transmitted in the analog domain.