Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
2.3
2.4
Journals
Photonics
Special Issues
Optical Computing and Optical Neural Networks
share announcement

Optical Computing and Optical Neural Networks

A special issue of Photonics (ISSN 2304-6732).

Deadline for manuscript submissions: 15 August 2024 | Viewed by 2405

Special Issue Editors

Dr. Bin Shi

E-Mail Website
Guest Editor
Eindhoven Hendrik Casimir Institute, Eindhoven University of Technology, 5600 MB Eindhoven, The Netherlands
Interests: neuromorphic photonics; photonic integration; optical beam steering; optical computing and switching
Dr. Apostolos Tsakyridis

E-Mail Website
Guest Editor
Department of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece
Interests: neuromorphic photonics; optical signal processing; linear optics
Special Issues, Collections and Topics in MDPI journals
Dr. Miltiadis Moralis-Pegios

E-Mail Website
Guest Editor
Photonic Systems and Networks Group, Aristotle University of Thessaloniki, Thessaloniki, Greece
Interests: neuromorphic photonics; optical interconnects; optical switching
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The current exponentially growing data volume demands computing power that grows apace. Artificial intelligence based on neural networks has achieved great success in solving complex problems involving the processing of huge amounts of data. Optical and photonic neural networks are alternative solutions to electronics, exploiting the high parallelisms from the nature of light to enhance the computing speed and power efficiency with parallel computing. The study of optical neural networks is important to the exploration of the related methods, designs, systems, and training algorithms to improve the performance when solving complex problems. Optical neural networks are an essential part of optical computing, and potentially provide solutions in low-latency and real time data processing. This Special Issue aims to present the recent advanced research in optical neural networks with different schemes within the topic of non-von Neumann computing. The implementations can be in free-space, fiber-optics, and photonic integrated circuits.

Dr. Bin Shi
Dr. Apostolos Tsakyridis
Dr. Miltiadis Moralis-Pegios
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Photonics is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • optical computing
  • neuromorphic computing
  • opto-electric neural networks
  • optical/photonic spiking neural networks
  • optical/photonic deep neural networks
  • optical/photonic convolutional neural networks
  • optical reservoir computing
  • opto-electric ising machine
  • optical training algorithms
  • optical systems for neural networks

Published Papers (2 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

13 pages, 2677 KiB  
Article
Scalable Photonic Digital-to-Analog Converters
by Md Mahadi Masnad, S. Mohammad Reza Safaee, Najla Najeeb, Kaveh Rahbardar Mojaver, Mohamed Fouda, Emanuel Peinke and Odile Liboiron-Ladouceur
Photonics 2024, 11(2), 112; https://doi.org/10.3390/photonics11020112 - 26 Jan 2024
Viewed by 924
Abstract
This work introduces a novel architecture for implementing a parallel coherent photonic digital-to-analog converter (PDAC), designed to transform parallel digital electrical signals into corresponding analog optical output, convertible to analog electrical signals using photodiodes. The proposed architecture incorporates microring resonator-based modulators (MRMs), phase [...] Read more.
This work introduces a novel architecture for implementing a parallel coherent photonic digital-to-analog converter (PDAC), designed to transform parallel digital electrical signals into corresponding analog optical output, convertible to analog electrical signals using photodiodes. The proposed architecture incorporates microring resonator-based modulators (MRMs), phase shifters, and symmetric multimode interference couplers. Efficient modulation is achieved by MRMs utilizing carrier depletion-induced refractive index changes, while metal heaters facilitate tuning of the ring resonator resonance wavelength. The proposed architecture is scalable to higher bit resolutions and exhibits a dynamic range limited by MRM’s sensitivity to applied bias and noise levels. Experimental results of the fabricated chip in the silicon-on-insulator (SOI) platform showcase the successful realization of a 4 GSample/sec conversion rate in a 2-bit resolution operation, along with a stationary conversion of four parallel DC digital signals into 16 analog intensity levels in a 4-bit PDAC configuration. The study encompasses a proof-of-concept experimental demonstration of 8 Gbps data conversion, along with a 50 Gbps data conversion rate using the optimized design in the simulation, affirming the accuracy and quality of the PDAC architecture. These findings contribute to the advancement of PDAC technology, providing insights into performance characteristics, limitations, and potential applications. Full article
(This article belongs to the Special Issue Optical Computing and Optical Neural Networks)
►▼ Show Figures

Figure 1

11 pages, 8213 KiB  
Article
Microcomb-Driven Optical Convolution for Car Plate Recognition
by Zhenming He, Junwei Cheng, Xinyu Liu, Bo Wu, Heng Zhou, Jianji Dong and Xinliang Zhang
Photonics 2023, 10(9), 972; https://doi.org/10.3390/photonics10090972 - 25 Aug 2023
Cited by 1 | Viewed by 975
Abstract
The great success of artificial intelligence (AI) calls for higher-performance computing accelerators, and optical neural networks (ONNs) with the advantages of high speed and low power consumption have become competitive candidates. However, most of the reported ONN architectures have demonstrated simple MNIST handwritten [...] Read more.
The great success of artificial intelligence (AI) calls for higher-performance computing accelerators, and optical neural networks (ONNs) with the advantages of high speed and low power consumption have become competitive candidates. However, most of the reported ONN architectures have demonstrated simple MNIST handwritten digit classification tasks due to relatively low precision. A microring resonator (MRR) weight bank can achieve a high-precision weight matrix and can increase computing density with the assistance of wavelength division multiplexing (WDM) technology offered by dissipative Kerr soliton (DKS) microcomb sources. Here, we implement a car plate recognition task based on an optical convolutional neural network (CNN). An integrated DKS microcomb was used to drive an MRR weight-bank-based photonic processor, and the computing precision of one optical convolution operation could reach 7 bits. The first convolutional layer was realized in the optical domain, and the remaining layers were performed in the electrical domain. Totally, the optoelectronic computing system (OCS) could achieve a comparable performance with a 64-bit digital computer for character classification. The error distribution obtained from the experiment was used to emulate the optical convolution operation of other layers. The probabilities of the softmax layer were slightly degraded, and the robustness of the CNN was reduced, but the recognition results were still acceptable. This work explores an MRR weight-bank-based OCS driven by a soliton microcomb to realize a real-life neural network task for the first time and provides a promising computational acceleration scheme for complex AI tasks. Full article
(This article belongs to the Special Issue Optical Computing and Optical Neural Networks)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-2
Back to TopTop