End-to-end learning in communication systems
A technology of transmission system and transmitter, applied in baseband system, transmission system, digital transmission system, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0036] figure 1is a block diagram of an example end-to-end communication system implemented as a neural network, generally indicated by reference numeral 1, in which example embodiments may be implemented. System 1 includes transmitter 2 , channel 4 and receiver 6 . Viewed at the system level, system 1 converts input symbol(s) (also called messages) received at the input to transmitter 2 into output symbols at the output of receiver 6
[0037] Transmitter 2 implements the transmitter algorithm. Similarly, receiver 6 implements a receiver algorithm. As described in detail below, the algorithms of the transmitter 2 and receiver 6 are trained in order to optimize the performance of the system 1 as a whole.
[0038] System 1 thus provides an autoencoder implementing an end-to-end communication system. Autoencoders can be trained with respect to any loss function related to some performance metric, such as Block Error Rate (BLER). (The terms "autoencoder" and "communication ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


