98%
921
2 minutes
20
Matrix computation, as a fundamental building block of information processing in science and technology, contributes most of the computational overheads in modern signal processing and artificial intelligence algorithms. Photonic accelerators are designed to accelerate specific categories of computing in the optical domain, especially matrix multiplication, to address the growing demand for computing resources and capacity. Photonic matrix multiplication has much potential to expand the domain of telecommunication, and artificial intelligence benefiting from its superior performance. Recent research in photonic matrix multiplication has flourished and may provide opportunities to develop applications that are unachievable at present by conventional electronic processors. In this review, we first introduce the methods of photonic matrix multiplication, mainly including the plane light conversion method, Mach-Zehnder interferometer method and wavelength division multiplexing method. We also summarize the developmental milestones of photonic matrix multiplication and the related applications. Then, we review their detailed advances in applications to optical signal processing and artificial neural networks in recent years. Finally, we comment on the challenges and perspectives of photonic matrix multiplication and photonic acceleration.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8814250 | PMC |
http://dx.doi.org/10.1038/s41377-022-00717-8 | DOI Listing |
Genet Sel Evol
August 2025
The Roslin Institute and Royal (Dick) School of Veterinary Studies, University of Edinburgh, Midlothian, EH25 9RG, UK.
Background: Pedigrees continue to be extremely important in agriculture and conservation genetics, with the pedigrees of modern breeding programmes easily comprising millions of records. This size can make visualising the structure of such pedigrees challenging. Being graphs, pedigrees can be represented as matrices, including, most commonly, the additive (numerator) relationship matrix, , and its inverse.
View Article and Find Full Text PDFNature
August 2025
Key Laboratory of Pressure Systems and Safety, Ministry of Education, East China University of Science and Technology, Shanghai, China.
The mechanical properties of metallic materials often degrade under harsh cryogenic conditions, posing challenges for low-temperature infrastructures. Here we introduce a dual-scale atomic-ordering nanostructure, characterized by an exceptionally high number density of co-existing subnanoscale short-range ordering (approximately 2.4 × 10 m) and nanoscale long-range ordering (approximately 4.
View Article and Find Full Text PDFJ Dairy Res
August 2025
InovaLeite - Laboratório de Pesquisa em Leites e Derivados, Departamento de Tecnologia de Alimentos, Universidade Federal de Viçosa, Viçosa, MG, Brazil.
Whey, a greenish-yellow liquid resulting from curd separation in cheese manufacturing, was historically considered economically insignificant in the dairy industry and often discarded into the environment without proper oversight. However, recognizing its high nutritional value, whey has become a valuable ingredient in the food industry. Unprocessed whey (raw material) is highly susceptible to contamination, as it can serve as a substrate for the multiplication of a range of microorganisms, including spoilage, spore forming, pathogenic and toxin producing bacteria, particularly if stored at inappropriate temperatures.
View Article and Find Full Text PDFIEEE Trans Pattern Anal Mach Intell
August 2025
The lottery ticket hypothesis (LTH) has increased attention to pruning neural networks at initialization. We study this problem in the linear setting. We show that finding a sparse mask at initialization is equivalent to the sketching problem introduced for efficient matrix multiplication.
View Article and Find Full Text PDFPhotonic systems excel at performing linear computations, such as matrix-vector multiplications, in a highly parallel and energy-efficient manner. However, implementing nonlinear computations in photonic systems remains challenging without relying on optoelectronic conversions or nonlinear/active materials, both of which are energy-intensive. Here, we present a nonlinear computing approach for time series processing.
View Article and Find Full Text PDF