All-optical temporal integration mediated by subwavelength heat antennas

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yi, Farmakidis, Nikolaos, Roumpos, Ioannis, Moralis-Pegios, Miltiadis, Tsakyridis, Apostolos, Lee, June Sang, Dong, Bowei, He, Yuhan, Aggarwal, Samarth, Pleros, Nikolaos, Bhaskaran, Harish
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915427807920128
author Zhang, Yi
Farmakidis, Nikolaos
Roumpos, Ioannis
Moralis-Pegios, Miltiadis
Tsakyridis, Apostolos
Lee, June Sang
Dong, Bowei
He, Yuhan
Aggarwal, Samarth
Pleros, Nikolaos
Bhaskaran, Harish
author_facet Zhang, Yi
Farmakidis, Nikolaos
Roumpos, Ioannis
Moralis-Pegios, Miltiadis
Tsakyridis, Apostolos
Lee, June Sang
Dong, Bowei
He, Yuhan
Aggarwal, Samarth
Pleros, Nikolaos
Bhaskaran, Harish
contents Optical computing systems deliver unrivalled processing speeds for scalar operations. Yet, integrated implementations have been constrained to low-dimensional tensor operations that fall short of the vector dimensions required for modern artificial intelligence. We demonstrate an all-optical neuromorphic computing system based on time division multiplexing, capable of processing input vectors exceeding 250,000 elements within a unified framework. The platform harnesses optically driven thermo-optic modulation in standing wave optical fields, with titanium nano-antennas functioning as wavelength-selective absorbers. Counterintuitively, the thermal time dynamics of the system enable simultaneous time integration of ultra-fast (50GHz) signals and the application of programmable, non-linear activation functions, entirely within the optical domain. This unified framework constitutes a leap towards large-scale photonic computing that satisfies the dimensional requirements of AI workloads.
format Preprint
id arxiv_https___arxiv_org_abs_2505_04405
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle All-optical temporal integration mediated by subwavelength heat antennas
Zhang, Yi
Farmakidis, Nikolaos
Roumpos, Ioannis
Moralis-Pegios, Miltiadis
Tsakyridis, Apostolos
Lee, June Sang
Dong, Bowei
He, Yuhan
Aggarwal, Samarth
Pleros, Nikolaos
Bhaskaran, Harish
Optics
Artificial Intelligence
Applied Physics
Optical computing systems deliver unrivalled processing speeds for scalar operations. Yet, integrated implementations have been constrained to low-dimensional tensor operations that fall short of the vector dimensions required for modern artificial intelligence. We demonstrate an all-optical neuromorphic computing system based on time division multiplexing, capable of processing input vectors exceeding 250,000 elements within a unified framework. The platform harnesses optically driven thermo-optic modulation in standing wave optical fields, with titanium nano-antennas functioning as wavelength-selective absorbers. Counterintuitively, the thermal time dynamics of the system enable simultaneous time integration of ultra-fast (50GHz) signals and the application of programmable, non-linear activation functions, entirely within the optical domain. This unified framework constitutes a leap towards large-scale photonic computing that satisfies the dimensional requirements of AI workloads.
title All-optical temporal integration mediated by subwavelength heat antennas
topic Optics
Artificial Intelligence
Applied Physics
url https://arxiv.org/abs/2505.04405