Key Technologies of Photonic Artificial Intelligence Chip Structure and Algorithm

Pei, Li; Xi, Zeya; Bai, Bing; Wang, Jianshuai; Zuo, Xiaoyan; Ning, Tigang; Jiao, Z.; Li, Jing

doi:10.3390/app11125719

Cited by 3 publications

(2 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Assuming that any football pattern x i is a observable random vector and its set is { x 1 ,…, x n }, the vector formula is Ex( x ), the covariance matrix is Co( x ), and the factor calculation formula of different vectors is shown as follows [ 9 ]:

where ξ is the adjustment error of the factor. Assuming that the correlation of any football pattern is f j , which is a random observable vector and its set is { y 1 ,…, y m }, the vector formula is F ( x ), the covariance diagonal matrix is E ( x )=Σ, and the correlation calculation formula of different factors is shown as follows:

where τ is the adjustment error of correlation [ 10 ].…”

Section: Relevant Modelsmentioning

confidence: 99%

A Study on the Optimization and Improvement of the Construction of the Campus Football Development Model by a Factor Analysis Method under the Background of “Healthy China”

Wang

Tan

2022

Journal of Environmental and Public Health

View full text Add to dashboard Cite

In order to enrich campus sport life and promote the development of campus ball game, this paper uses the analysis method to analyze the development mode of campus football and evaluates the relevant factors combined with the development status, characteristics, and future trend of campus football. Factor analysis is a comprehensive analysis method, which can realize multifactor comprehensive analysis and qualitative and quantitative analysis of campus football. At the same time, analyze the relationship between various factors and find a scheme conducive to the development of campus football. The results show that both comprehensive method factors and single method factors are positive, indicating that the two models have a significant positive impact on the development model of students’ football. However, the influence degree of the comprehensive method (0.314) is the largest, followed by the single method factor (0.128), and the sig. values of the two variable factors are <0.05, so the comprehensive method is the main mode of campus football development. Therefore, the factor analysis method proposed in this paper is conducive to the selection of campus football development model and provides support for the development of campus football.

show abstract

where τ is the adjustment error of correlation [ 10 ].…”

Section: Relevant Modelsmentioning

confidence: 99%

A Study on the Optimization and Improvement of the Construction of the Campus Football Development Model by a Factor Analysis Method under the Background of “Healthy China”

Wang

Tan

2022

Journal of Environmental and Public Health

View full text Add to dashboard Cite

show abstract

“…ANN can be divided into feedforward neural network (FNN), convolution neural network (CNN), and recursive neural network (RNN) according to different calculation tasks [22]. FNN is the simplest one-way neural network, including input layer, hidden layer, and output layer [23,24].…”

Section: Introductionmentioning

confidence: 99%

Implementation of optical neural network based on Mach–Zehnder interferometer array

Yuan

et al. 2022

IET Optoelectronics

View full text Add to dashboard Cite

Compared with electrons, photons have the potential to realise ultra-high speed operations because of its unique high speed and high parallelism. In recent years, there have been many researches on neural networks using optical hardware. The Mach-Zehnder interferometer (MZI) and micro-ring resonator (MRR) are commonly used as optical devices to realise linear operation units in optical neural networks (ONN). MZI has the advantages of simple fabrication, high sensitivity, and easy integration, which has attracted the attention of researchers. We summarise the implementation methods of ONN matrix multiplication based on MZI, the implementation methods of non-linear activation, and the on-chip training methods. We first summarise the researches on matrix multiplication of ONN based on MZI. Three kinds of MZI grid decomposition methods, Fast Fourier Transform (FFT) grid structures, and the corresponding derivation processes are introduced, respectively. Then, several experimental implementations of ONN based on MZI are summarised, and the characteristics of optical processors fabricated in these references are analysed. Finally, the realisation methods of non-linear activation and on-chip training of silicon ONN are introduced, respectively.

show abstract

Fast waveguide geometry extraction using an optical measurement method

Liu

et al. 2023

AOPC 2022: Optoelectronics and Nanophotonics

View full text Add to dashboard Cite

A kind of waveguide geometry extraction method based on optical measurements was proposed. By designing two Mach-Zehnder interferometers (MZIs) with different arm lengths, the width and height of the physical geometry of fabricated waveguides could be accurately extracted with the help of MZIs' optical measured spectrum results. The extracted results on the CUMEC multi-project wafer service (MPW) showed that the mean width and height of the fabricated waveguide were 463.46 nm and 213.58 nm, respectively, while their standard deviation values were 3.82 nm and 2.13 nm, respectively.

show abstract

Key Technologies of Photonic Artificial Intelligence Chip Structure and Algorithm

Cited by 3 publications

References 44 publications

A Study on the Optimization and Improvement of the Construction of the Campus Football Development Model by a Factor Analysis Method under the Background of “Healthy China”

A Study on the Optimization and Improvement of the Construction of the Campus Football Development Model by a Factor Analysis Method under the Background of “Healthy China”

Implementation of optical neural network based on Mach–Zehnder interferometer array

Fast waveguide geometry extraction using an optical measurement method

Contact Info

Product

Resources

About