End-to-end deep learning for communication systems, i.e., the complete process of training the embeddings for the messages, dense NN to convert the embeddings into signal constellation and training the decoder to decode the received corrupted signal is carried out at one go. These encoder-decoder systems can achieve bit error rates which come close to practical baseline techniques if they are used for over-the-air transmissions. This is promising since complex encoding and decoding functions can be learned on the fly without extensive communication-theoretic analysis and design, possibly enabling future communication systems to better cope with new and changing channel scenarios.
We studied and implemented the paper "Deep Learning for Channel Coding via Neural Mutual Information Estimation", which tries to develop a neural network to learn efficient encoding scheme without knowing the channel probability distribution. Moreover, this encoder-decoder pair achieved average symbol error rate almost equal to 16-QAM.
shaan3130/Channel-Encoding-using-Neural-Network
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
We studied and implemented the paper "Deep Learning for Channel Coding via Neural Mutual Information Estimation", which tries to develop a neural network to learn efficient encoding scheme without knowing the channel probability distribution. Moreover, this encoder-decoder pair achieved average symbol error rate almost equal to 16-QAM.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published