We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Fiber optic computing using distributed feedback.
- Authors
Redding, Brandon; Murray, Joseph B.; Hart, Joseph D.; Zhu, Zheyuan; Pang, Shuo S.; Sarma, Raktim
- Abstract
The widespread adoption of machine learning and other matrix intensive computing algorithms has 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 optical techniques rely on spatial multiplexing, requiring a large number of modulators and detectors, and are typically 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. Using Rayleigh backscattering in standard single mode fiber, we show that this technique can efficiently apply a series of random nonlinear projections to the input data, facilitating a variety of computing tasks. The approach enables efficient energy scaling with orders of magnitude lower power consumption than GPUs, while maintaining low latency and high data-throughput. Optical techniques adopted in optical computing rely on spatial multiplexing, requiring numerous integrated elements and restricting the architecture to perform a single kernel convolution per layer. The authors demonstrate a fiber-optic computing architecture based on temporal multiplexing that performs multiple convolutions in a single layer.
- Subjects
OPTICAL computing; DIGITAL electronics; DISTRIBUTED computing; MATRIX multiplications; MACHINE learning
- Publication
Communications Physics, 2024, Vol 7, Issue 1, p1
- ISSN
2399-3650
- Publication type
Article
- DOI
10.1038/s42005-024-01549-1