EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Photonic neural networks and optics-informed deep learning fundamentals

Apostolos Tsakyridis, Miltiadis Moralis-Pegios, George Giamougiannis, Manos Kirtas, Nikolaos Passalis, Anastasios Tefas, Nikos Pleros

APL Photonics · 01.01.2024 · 9 (1)

DOI: 10.1063/5.0169810 ↗

Kurz gefasst

Fachartikel in der Zeitschrift APL Photonics, online erschienen am 29.01.2024. Verfasst von Apostolos Tsakyridis und 6 weiteren Autor:innen. Die Arbeit wurde bisher 80-mal zitiert (Crossref) und nennt 172 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Horizon 2020 Framework Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The recent explosive compute growth, mainly fueled by the boost of artificial intelligence (AI) and deep neural networks (DNNs), is currently instigating the demand for a novel computing paradigm that can overcome the insurmountable barriers imposed by conventional electronic computing architectures. Photonic neural networks (PNNs) implemented on silicon integration platforms stand out as a promising candidate to endow neural network (NN) hardware, offering the potential for energy efficient and ultra-fast computations through the utilization of the unique primitives of photonics, i.e., energy efficiency, THz bandwidth, and low-latency. Thus far, several demonstrations have revealed the huge potential of PNNs in performing both linear and non-linear NN operations at unparalleled speed and energy consumption metrics. Transforming this potential into a tangible reality for deep learning (DL) applications requires, however, a deep understanding of the basic PNN principles, requirements, and challenges across all constituent architectural, technological, and training aspects. In this Tutorial, we, initially, review the principles of DNNs along with their fundamental building blocks, analyzing also the key mathematical operations needed for their computation in photonic hardware. Then, we investigate, through an intuitive mathematical analysis, the interdependence of bit precision and energy efficiency in analog photonic circuitry, discussing the opportunities and challenges of PNNs. Followingly, a performance overview of PNN architectures, weight technologies, and activation functions is presented, summarizing their impact in speed, scalability, and power consumption. Finally, we provide a holistic overview of the optics-informed NN training framework that incorporates the physical properties of photonic building blocks into the training process in order to improve the NN classification accuracy and effectively elevate neuromorphic photonic hardware into high-performance DL computational settings.

Förderung

  • Horizon 2020 Framework Program

Zitieren

APA

Tsakyridis, A., Moralis-Pegios, M., Giamougiannis, G., Kirtas, M., Passalis, N., Tefas, A., & Pleros, N. (2024). Photonic neural networks and optics-informed deep learning fundamentals. APL Photonics, 9(1). https://doi.org/10.1063/5.0169810

Vancouver

Tsakyridis A, Moralis-Pegios M, Giamougiannis G, Kirtas M, Passalis N, Tefas A, et al. Photonic neural networks and optics-informed deep learning fundamentals. APL Photonics. 2024;9(1). doi:10.1063/5.0169810

BibTeX
@article{Tsakyridis2024,
  author = {Tsakyridis, Apostolos and Moralis-Pegios, Miltiadis and Giamougiannis, George and Kirtas, Manos and Passalis, Nikolaos and Tefas, Anastasios and Pleros, Nikos},
  title = {Photonic neural networks and optics-informed deep learning fundamentals},
  journal = {APL Photonics},
  year = {2024},
  volume = {9},
  number = {1},
  doi = {10.1063/5.0169810}
}
Infokarte | EUVIMED

Artikeldaten derzeit nicht verfügbar.

Recherche