JS2498/Model_Free_E2E_Communication
Implementation of the paper "Model Free Training of End-to-End Communication Systems"
This project helps communication systems engineers design robust wireless communication links when the exact characteristics of the transmission channel are unknown or difficult to model mathematically. It takes message data and simulates its transmission through various noisy, unpredictable channels, producing an optimized system for reliably decoding those messages on the other end. Communication system designers can use this to develop better wireless transceivers.
No commits in the last 6 months.
Use this if you need to train both the transmitter and receiver components of a communication system when the channel between them is complex, unpredictable, or doesn't have a clear mathematical model.
Not ideal if your communication channel is perfectly known and differentiable, as traditional backpropagation methods would be more straightforward.
Stars
16
Forks
4
Language
Jupyter Notebook
License
—
Category
Last pushed
Aug 06, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/JS2498/Model_Free_E2E_Communication"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
NVlabs/sionna
Sionna: An Open-Source Library for Research on Communication Systems
lab-emi/OpenDPD
OpenDPD is an end-to-end learning framework built in PyTorch for power amplifier (PA) modeling...
utcsilab/score-based-channels
Source code for paper "MIMO Channel Estimation using Score-Based Generative Models", published...
DeepMIMO/DeepMIMO
DeepMIMOv4: A Toolchain and Database for Ray-tracing Datasets.
NVlabs/neural_rx
Real-Time Inference of 5G NR Multi-user MIMO Neural Receivers