Mode identification method and device

A pattern recognition and recognition technology, applied in the computer field, can solve the problems of increasing the number of model parameters, low accuracy, and inability to fully integrate context information, etc., to achieve the effect of improving accuracy and increasing depth

Active Publication Date: 2015-07-22
TSINGHUA UNIV
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] First of all, because the convolutional neural network is a pure feedforward structure, it cannot fully integrate context information during recognition, and context information has an important impact on the recognition effect
[0005] In addition, the depth of the network has a great influence on the recognition performance, and the recognition accuracy will increase with the increase of the depth, while the depth of the convolutional layer of the convolutional neural network is fixed at 1. To increase the depth of t

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
  • Mode identification method and device
  • Mode identification method and device
  • Mode identification method and device

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0024] Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowchart describes the operations as sequential processing, many of the operations can be implemented in parallel, concurrently, or simultaneously. In addition, the order of operations can be rearranged. The processing may be terminated when its operation is completed, but may also have additional steps not included in the drawings. The processing may correspond to methods, functions, procedures, subroutines, subroutines, and so on.

[0025] The computer equipment includes user equipment and network equipment. The user equipment includes, but is not limited to, computers, smart phones, PDAs, etc.; the network equipment includes, but is not limited to, a single network server, a server group composed of multiple network servers, or a large number of computers based on Cloud Computing....

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 provides a mode identification method and a mode identification device. The mode identification method comprises the following steps: receiving data to be identified; performing mode identification on data to be identified by using a mode identification model obtained through training based on a convolutional neural network with a recursion convolutional layer, wherein the convolutional neural network with the recursion convolutional layer is a neural network that total input is obtained with the combination of in-layer recursion input on the basis of feedforward input and the total input is subjected to non-linear stimulation. The convolutional neural network with the recursion convolutional layer can be sufficiently fused in the context information, and under the condition that the parameter number is kept unchanged, the depth of the network can be increased, so that the mode identification accuracy can be effectively improved.

Description

technical field [0001] The invention relates to the field of computers, in particular to a pattern recognition method and device. Background technique [0002] Pattern recognition is used to recognize the input pattern and output the category of the pattern. Examples include but are not limited to: face recognition, gesture recognition, traffic sign recognition, voice recognition, etc. [0003] The pattern recognition method in the prior art is based on neural network training to obtain a pattern recognition model, and uses the trained pattern recognition model to recognize the category of the pattern. Among them, using a convolutional neural network (CNN, Convolutional Neural Network) to train a pattern recognition model is a relatively common training method. However, the inventors have found that there are at least the following problems in the training of pattern recognition models using existing convolutional neural networks: [0004] First of all, because the convol...

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
IPC IPC(8): G06K9/62G06N3/04
CPCG06N3/04G06F18/285
Inventor 胡晓林梁鸣
Owner TSINGHUA UNIV
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