Supercharge Your Innovation With Domain-Expert AI Agents!

Coding method, decoding method and device

An encoding method and encoding technology, which are applied in the fields of encoding methods, decoding methods and devices, can solve problems such as high difficulty in implementation and increased complexity of code word space traversal

Active Publication Date: 2021-10-15
HUAWEI TECH CO LTD
View PDF14 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, when the number of information bits in the existing technology is large, the complexity of traversing the entire codeword space increases dramatically, making it difficult to implement

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
  • Coding method, decoding method and device
  • Coding method, decoding method and device
  • Coding method, decoding method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0114] scene one

[0115] Combine figure 1 ,like Figure 4 The flow diagram of the encoding method in the present application embodiment is Figure 4 middle:

[0116] Step 101 generate a neural network unit.

[0117] Specifically, in the embodiment of the present application, the encoding apparatus can generate an initial neural network unit based on the core matrix. Subsequently, the encoding device is trained to the initial neural network unit, so that the output value of the initial neural network unit is close to the desired optimization target. Then, the initial neural network unit after training is the neural network unit. Among them, the initial neuron parameters contained in the initial neural network unit have been trained, and the neuron parameters contained in the neural network unit are updated. And, the output value is close to the desired optimization target, that is, the error between the output information output of the initial network unit and the input information ...

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 present application provides an encoding and decoding method and device, which relate to the communication field. The method can generate corresponding neural network units based on the kernel matrix, and then form the neural network units into an encoding neural network or a decoding neural network, realizing After connecting the small neural network units, the encoding neural network or decoding neural network is obtained, so that in the learning process of encoding / decoding, it can be generalized to the entire code word space through small learning samples, and the weakening has a relatively large The influence of long codeword information on the complexity and learning difficulty of the neural network.

Description

Technical field [0001] The present application embodiment relates to the field of communication, and more particularly to an encoding method, a decoding method, and a device. Background technique [0002] Currently, in the process of prior technology encoding / decoding, the encoding / decoder needs to learn the samples of the entire codeword space, and the specialty of polarization code (Polar) is long, resulting in a code length. Increased, its corresponding total code this spatial code sequence has exponentially amplified. Therefore, the prior art is large when the number of information is large, resulting in sharp increase in complexity of the entire codeword space traversal, and the difficulty is relatively difficult. Inventive content [0003] The present application provides an encoding method, a decoding method, and a device that can weaken the impact of the code length on the code space traversal, thereby improving the learning efficiency of coding / decoding. [0004] ...

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): H03M13/13G06N3/04G06N3/08
CPCH03M13/13G06N3/084G06N3/045H03M13/6597H04L25/03165G06F18/24133G06F18/214G06F17/16G06N3/08G06F18/22
Inventor 徐晨李榕于天航乔云飞杜颖钢黄凌晨王俊
Owner HUAWEI TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com