Deep Binarized Photonic Reservoir Computing for Ultrafast Multimedia Signal Processing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Iqbal, Muhammad Waqar, Alassir, Mohamad, Marsal, Nicolas, Rontani, Damien
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916061731880960
author Iqbal, Muhammad Waqar
Alassir, Mohamad
Marsal, Nicolas
Rontani, Damien
author_facet Iqbal, Muhammad Waqar
Alassir, Mohamad
Marsal, Nicolas
Rontani, Damien
contents We present a deep photonic neural network architecture based on ultrafast binary optical modulation from a digital micro-mirror device (DMD), optical scattering in random medium, high-speed photodetection with a CMOS sensor, and time-multiplexed deep layer structure. Operating at Gigabit-per-second (Gb/s) processing rates, our system based on the reservoir computing (RC) framework achieves state-of-the-art performance across various multimedia tasks, including video, image and speech recognition. We show that the careful optimization of key physical intra- and inter-layer hyper-parameters can significantly enhance the deep photonic RC system ability to extract relevant temporal and spatial features via balancing memory retention and dynamical response of individual layers. This approach paves the way for highly scalable hierarchical photonic reservoir computing systems for high-throughput real-time multimedia signal processing.
format Preprint
id arxiv_https___arxiv_org_abs_2605_30149
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Deep Binarized Photonic Reservoir Computing for Ultrafast Multimedia Signal Processing
Iqbal, Muhammad Waqar
Alassir, Mohamad
Marsal, Nicolas
Rontani, Damien
Neural and Evolutionary Computing
Optics
We present a deep photonic neural network architecture based on ultrafast binary optical modulation from a digital micro-mirror device (DMD), optical scattering in random medium, high-speed photodetection with a CMOS sensor, and time-multiplexed deep layer structure. Operating at Gigabit-per-second (Gb/s) processing rates, our system based on the reservoir computing (RC) framework achieves state-of-the-art performance across various multimedia tasks, including video, image and speech recognition. We show that the careful optimization of key physical intra- and inter-layer hyper-parameters can significantly enhance the deep photonic RC system ability to extract relevant temporal and spatial features via balancing memory retention and dynamical response of individual layers. This approach paves the way for highly scalable hierarchical photonic reservoir computing systems for high-throughput real-time multimedia signal processing.
title Deep Binarized Photonic Reservoir Computing for Ultrafast Multimedia Signal Processing
topic Neural and Evolutionary Computing
Optics
url https://arxiv.org/abs/2605.30149