arXiv · 2411.00189
Photonic neural networks with spatiotemporal chaos in multimode fibers
Abstract
Optical computing has gained significant attention as a potential solution to the growing computational demands of machine learning, particularly for tasks requiring large-scale data processing and high energy efficiency. Optical systems offer promising alternatives to digital neural networks by exploiting light's parallelism. This study explores a photonic neural network design using spatiotemporal chaos within grad-ed-index multimode fibers to improve machine learning performance. Through numerical simulations and experiments, we show that chaotic light propagation in multimode fibers enhances data classification accu-racy across domains, including biomedical imaging, fashion, and satellite geospatial analysis. This chaotic optical approach enables high-dimensional transformations, amplifying data separability and differentiation for greater accuracy. Fine-tuning parameters such as pulse peak power optimizes the reservoir's chaotic properties, highlighting the need for careful calibration. These findings underscore the potential of chaos-based nonlinear photonic neural networks to advance optical computing in machine learning, paving the way for efficient, scalable architectures.
Explore related subjects
Keep this discovery
Bahadır Utku Kesgin, Uğur Teğin. 2024-10-31. Photonic neural networks with spatiotemporal chaos in multimode fibers. https://arxiv.org/abs/2411.00189
Cite the original work for its findings. Save a collection to share your selection of sources.