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

An auto-encoder and method and medium for training auto-encoder

A technology of automatic encoder and encoder, applied in the field of automatic encoder

Pending Publication Date: 2020-06-02
FUJITSU LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these autoencoders mentioned above do not solve this problem well

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
  • An auto-encoder and method and medium for training auto-encoder
  • An auto-encoder and method and medium for training auto-encoder
  • An auto-encoder and method and medium for training auto-encoder

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] Examples of the present disclosure will now be described more fully with reference to the accompanying drawings. The following description is merely exemplary in nature and is not intended to limit the disclosure, application or uses.

[0023] Example embodiments are provided so that this disclosure will be thorough, and will fully convey the scope to those who are skilled in the art. Numerous specific details are set forth such as examples of specific components, devices and methods, to provide a thorough understanding of embodiments of the present disclosure. It will be apparent to those skilled in the art that specific details need not be employed, that example embodiments may be embodied in many different forms, and that neither should be construed to limit the scope of the disclosure. In some example embodiments, well-known processes, well-known structures, and well-known technologies are not described in detail.

[0024] As described in the following expression ...

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

Disclosed are an auto-encoder and a method and medium for training the auto-encoder. The auto-encoder comprises: an encoder unit that maps input data into hidden variables in a hidden space; a constraint unit which is used for applying constraint to the hidden variables, so that the hidden variables are gathered around a central point in the hidden space; a decoder unit that decodes the hidden variables from the constraint unit into reconstructed data, in which the encoder unit, the constraint unit, and the decoder unit are trained such that the reconstructed data approximately matches the input data. According to the automatic encoder disclosed by the invention, the hidden variables of the similar data can be expressed in a local hidden space, so that the similar data is far away from thedissimilar data in the hidden space.

Description

technical field [0001] The present disclosure relates to the technical field of machine learning, in particular to an autoencoder and a method for training the autoencoder. Background technique [0002] This section provides background information related to the present disclosure which is not necessarily prior art. [0003] Autoencoders are a method of learning data representations in an unsupervised manner. It encodes the input data to obtain a shorter-length code, which is usually called a hidden variable. Then the code is decoded to obtain output data, wherein the output data is as close as possible to the input data. Autoencoders have a wide range of applications, such as data dimensionality reduction, denoising, etc. [0004] Traditional autoencoders implement model training through reconstruction errors. In recent years, research on autoencoders has mainly focused on imposing constraints on hidden variables to improve the ability of autoencoders to learn data repr...

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): H03M7/30G06N20/00G06K9/62
CPCH03M7/3059G06N20/00G06F18/22
Inventor 田虎李斐
Owner FUJITSU LTD
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