Method and device for generating identification model

A technology for identifying models and initial models, applied to biological neural network models, character and pattern recognition, instruments, etc., can solve problems such as time-consuming and relying on human expert engineering

Pending Publication Date: 2021-02-09
BEIJING WODONG TIANJUN INFORMATION TECH CO LTD +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the structure of deep neural networks is generally designed based on expert experience, which takes a lot of time and relies on a large number of human expert engineering.

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
  • Method and device for generating identification model
  • Method and device for generating identification model
  • Method and device for generating identification model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present disclosure will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain related inventions, rather than to limit the invention. It should also be noted that, for the convenience of description, only the parts related to the related invention are shown in the drawings.

[0036] It should be noted that, in the case of no conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and embodiments.

[0037] figure 1 An exemplary system architecture 100 to which the method for generating a recognition model or the apparatus for generating a recognition model of the present disclosure can be applied is shown.

[0038] Such as figure 1 As shown, the system architectu...

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 embodiment of the invention discloses a method and device for generating an identification model. The method comprises the steps of obtaining an initial model and a sample data set constructed based on a neural network; based on the sample data set iterative training initial model, in the iterative training process, executing the structure search operation according to a preset time table, wherein the preset time table is used for indicating the moment of determining the conversion operation between neurons in the iterative process, and the preset time table is associated with the number of iterations of the completed iterative operation; wherein the structure search operation comprises determining a conversion operation between neurons in the initial model from a preset operation setbased on parameters obtained by updating the initial model in the iterative operation; and generating a recognition model based on the conversion operation among the neurons in the initial model obtained after training and the parameters of the initial model obtained after training. Automatic design of the neural network model structure for task identification is realized.

Description

technical field [0001] Embodiments of the present disclosure relate to the field of computer technology, specifically to the field of artificial intelligence technology, and in particular to a method and device for generating a recognition model. Background technique [0002] With the development of artificial intelligence technology, deep neural networks are widely used in various fields. For example, in typical video recognition scenarios, the development of deep neural networks has pushed the limits of video recognition and achieved remarkable results. [0003] In order to ensure that the deep neural network achieves good results in the recognition task, it is necessary to optimize the model by adjusting the parameters of the network through iterative training on the basis of an effective and general network structure. Currently, the structure of deep neural networks is generally designed based on expert experience, which takes a lot of time and relies on a lot of human ...

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 Applications(China)
IPC IPC(8): G06N3/04G06N3/06G06K9/62
CPCG06N3/061G06N3/045G06F18/214
Inventor 姚霆梅涛
Owner BEIJING WODONG TIANJUN INFORMATION TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap