Multi-layer automatic coding method based on deep learning and system thereof

A technology of automatic coding and deep learning, applied in the field of deep learning, to achieve the effect of robust feature extraction and pattern learning

Inactive Publication Date: 2017-07-07
SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
View PDF0 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, it is necessary to provide a multi-layer auto-encoding method based on deep learning to solve the problem that the above-mentioned auto-encoder mainly adopts vector form for the expression of original data.

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
  • Multi-layer automatic coding method based on deep learning and system thereof
  • Multi-layer automatic coding method based on deep learning and system thereof
  • Multi-layer automatic coding method based on deep learning and system thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] In order to make the object, technical solution and advantages of the present invention clearer, the present invention 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 the present invention, not to limit the present invention.

[0036] Tensor theory is a branch of mathematics that satisfies the property that all laws of physics must be independent of the choice of coordinate system. The concept of tensor is a generalization of the concept of vector. Tensor is a multi-linear function that can be used to express the linear relationship between some vectors, scalars and other tensors. The samples used in tensor form can preserve the original structure to the greatest extent. , and then extract more robust features in the feature extraction stage, so the automatic encoding method of the present invention is based on deep learn...

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 present invention relates to a multi-layer automatic coding method and system based on deep learning. Combining the principle of deep learning and tensor algorithm, the original data is expressed in the form of tensor, which can fully excavate the original data without destroying the structure of the original data. The original information, and through multi-layer learning, obtain more essential abstract features, so as to overcome the limitations of vector expression, retain the structural information of the original data to a large extent, and obtain more robust feature extraction and pattern learning , which is conducive to the reflection of the essence of the original data and the subsequent pattern classification.

Description

technical field [0001] The present invention relates to the field of deep learning, in particular to a deep learning-based multi-layer automatic encoding method and system. Background technique [0002] Deep learning (Deep Learning) is a new field in machine learning research. Its purpose is to establish and simulate the neural network of human brain for analysis and learning. layer abstraction. Conventional processes include preprocessing, feature extraction, feature selection, recognition and prediction, etc. It is currently used in image recognition, speech recognition, natural language understanding, weather prediction, gene expression and other fields. [0003] Autoencoder (Autoencoder) is a compression encoder in the field of deep learning. The autoencoder will X o (The value range is [0, 1]) is the original data. First, the original data is mapped to a hidden layer and represented as X, which is expressed as the result of the reconstruction of the original data aft...

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): G06N3/08
CPCG06N3/082
Inventor 王书强李涵雄卢哲曾德威
Owner SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
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