Recurrent neural networks implemented through spatiotemporal light propagation in optical fibers

TL;DR

This paper demonstrates that multimode optical fibers can naturally implement recurrent neural network computations through passive light propagation, enabling energy-efficient temporal processing for various AI tasks without electronic feedback.

Contribution

It introduces a novel physical implementation of recurrent neural networks using spatiotemporal light dynamics in optical fibers, eliminating the need for trainable electronic components.

Findings

Achieved competitive performance on temporal tasks like time-series forecasting and action recognition.

Demonstrated energy-efficient processing leveraging intrinsic optical nonlinearities.

Showed that physical wave dynamics can serve as a basis for recurrent computation.

Abstract

Recurrent neural networks excel at temporal tasks and video processing but require energy-intensive sequential memory operations. We demonstrate that multimode optical fibers naturally implement spatiotemporal recurrent computation through passive light propagation. Video frames are encoded onto separate optical beams with controlled time delays; these beams combine and recirculate through a fiber loop where interference and nonlinear propagation generate high-dimensional states encoding both current inputs and fading memory. Remarkably, the entire optical system remains fixed with no trainable parameters or electronic feedback, yet this single physical configuration achieves competitive performance across diverse temporal and spatiotemporal learning tasks: chaotic time-series forecasting, human action recognition, steering angle prediction, and surgical skill assessment. Our results show that recurrent temporal processing can emerge directly from spatiotemporal wave dynamics. This paradigm shift from algorithmic to physical recurrence offers an energy-efficient pathway to temporal artificial intelligence by leveraging intrinsic spatiotemporal optical nonlinearities within multimode fibers.