Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Photoelectric hybrid intelligent data generation computing system and method

A data generation, photoelectric hybrid technology, applied in neural learning methods, biological neural network models, physical realization, etc., can solve problems such as limited work, achieve low power consumption, and realize the effect of large-scale high-speed data generation

Active Publication Date: 2022-08-09
TSINGHUA UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, the above-mentioned optical diffraction neural network can only implement machine learning discriminative models at present, and the work in the field of high-speed data generation using optical networks is very limited.
Unsupervised use of optical networks for automatic data generation is currently not possible and needs to be resolved

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Photoelectric hybrid intelligent data generation computing system and method
  • Photoelectric hybrid intelligent data generation computing system and method
  • Photoelectric hybrid intelligent data generation computing system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The following describes in detail the embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary, and are intended to explain the present invention and should not be construed as limiting the present invention.

[0029] The optoelectronic hybrid intelligent data generation computing system and system according to the embodiments of the present invention will be described below with reference to the drawings. First, the optoelectronic hybrid intelligent data generation computing system according to the embodiments of the present invention will be described with reference to the drawings.

[0030] figure 1 It is a schematic structural diagram of an optoelectronic hybrid intelligent data generation ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an optoelectronic hybrid intelligent data generation computing system and method, wherein the system comprises: an electronic compression sampling module for unsupervised learning of the feature probability distribution of input data, compressing the input information into a low-dimensional space and distributing it Sampling; feature conversion module, used to convert the compressed and sampled electronic characteristic signal into optical characteristic signal; all-optical data generation module, composed of multiple passive optical frequency domain modulation modules, used to generate the input optical characteristic signal Brand new calculation data. The system can realize intelligent data generation at the speed of light, enabling optoelectronic hybrid systems or all-optical machine learning to realize unsupervised intelligent data generation.

Description

technical field [0001] The invention relates to the technical field of optoelectronic computing and machine learning, and in particular, to a computing system and method for generating optoelectronic hybrid intelligent data. Background technique [0002] Generative models are one of the most important classes of models in machine learning. This type of model can generate observation data randomly, and can be used to directly model the data, or to establish conditional probability distributions among variables. The automatic generation of data such as images, texts, and sounds has been realized. [0003] At present, there is already an all-optical diffraction deep neural network, which realizes an all-optical machine learning discriminant model. The architecture optimizes the multi-level spatial frequency domain optical phase modulation layer and nonlinear layer combination similar to artificial neural network through machine learning design, and realizes functions such as ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06N3/067G06N3/08
CPCG06N3/0675G06N3/088
Inventor 戴琼海陈一彤乔晖鲍峰谢浩林星
Owner TSINGHUA UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com