Cover Image

Probabilistic photonic computing for AI

Probabilistic computing excels in approximating combinatorial problems and modeling uncertainty. However, using conventional deterministic hardware for probabilistic models is challenging: (pseudo) random number generation introduces computational overhead and additional data shuffling. Therefore, t...

Full description

Saved in:
Bibliographic Details
Main Authors: Brückerhoff-Plückelmann, Frank (Author) , Ovvyan, Anna (Author) , Varri, Akhil (Author) , Borras, Hendrik (Author) , Klein, Bernhard (Author) , Meyer, Lennart (Author) , Wright, C. David (Author) , Bhaskaran, Harish (Author) , Syed, Ghazi Sarwat (Author) , Sebastian, Abu (Author) , Fröning, Holger (Author) , Pernice, Wolfram (Author)
Format: Article (Journal)
Language:English
Published: 23 May 2025
In: Nature computational science
Year: 2025, Volume: 5, Issue: 5, Pages: 377-387
ISSN:2662-8457
DOI:10.1038/s43588-025-00800-1
Online Access:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1038/s43588-025-00800-1
Verlag, lizenzpflichtig, Volltext: https://www.nature.com/articles/s43588-025-00800-1
Get full text
Author Notes:Frank Brückerhoff-Plückelmann, Anna P. Ovvyan, Akhil Varri, Hendrik Borras, Bernhard Klein, Lennart Meyer, C. David Wright, Harish Bhaskaran, Ghazi Sarwat Syed, Abu Sebastian, Holger Fröning, and Wolfram Pernice
Description
Summary:Probabilistic computing excels in approximating combinatorial problems and modeling uncertainty. However, using conventional deterministic hardware for probabilistic models is challenging: (pseudo) random number generation introduces computational overhead and additional data shuffling. Therefore, there is a pressing need for different probabilistic computing architectures that achieve low latencies with reasonable energy consumption. Physical computing offers a promising solution, as these systems do not rely on an abstract deterministic representation of data but directly encode the information in physical quantities, enabling inherent probabilistic architectures utilizing entropy sources. Photonic computing is a prominent variant of physical computing due to the large available bandwidth, several orthogonal degrees of freedom for data encoding and optimal properties for in-memory computing and parallel data transfer. Here, we highlight key developments in physical photonic computing and photonic random number generation. We further provide insights into the realization of probabilistic photonic processors and their impact on artificial intelligence systems and future challenges.
Item Description:Gesehen am 28.10.2025
Physical Description:Online Resource
ISSN:2662-8457
DOI:10.1038/s43588-025-00800-1

Similar Items