US Patent Application 18345904. NEURAL NETWORK TRAINING METHOD AND RELATED APPARATUS simplified abstract

From WikiPatents
Jump to navigation Jump to search

NEURAL NETWORK TRAINING METHOD AND RELATED APPARATUS

Organization Name

HUAWEI TECHNOLOGIES CO., LTD.


Inventor(s)

Yan Sun of Shanghai (CN)


Yiqun Wu of Shanghai (CN)


NEURAL NETWORK TRAINING METHOD AND RELATED APPARATUS - A simplified explanation of the abstract

  • This abstract for appeared for US patent application number 18345904 Titled 'NEURAL NETWORK TRAINING METHOD AND RELATED APPARATUS'

Simplified Explanation

This abstract describes a method and apparatus for training a neural network. The method involves receiving channel sample information from a second device and using it to determine a neural network. This neural network is then used to perform inference and obtain additional channel sample information. The method aims to reduce signaling overheads, improve adaptability to different channel environments, and enhance communication performance.


Original Abstract Submitted

A neural network training method and a related apparatus are provided. The method includes: a first device receives first channel sample information from a second device. The first device determines a first neural network. The first neural network is obtained through training based on the first channel sample information, and is used to perform inference based on the first channel sample information to obtain second channel sample information. According to this method, air interface signaling overheads can be effectively reduced, adaptability to a channel environment is achieved, and communication performance is improved.