binzhou-com Goto Github PK

08052521_power

Reproducible research on the paper 'Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems'

aalto-dl-for-physical-layer

An Introduction to Deep Learning for the Physical Layer vs End-to-End Learning of Communications Systems Without a Channel Model

adjscc

adaptive/attention deep joint source channel coding

aff3ct

A fast simulator and a library dedicated to the channel coding.

amber

Autoencoder and Model Based Elimination of features using Relevance and Redundancy scores (AMBER) submitted to ICLR 2020

autoencoder-based-communication-system

Tensorflow Implementation and result of Auto-encoder Based Communication System From Research Paper : "An Introduction to Deep Learning for the Physical Layer" http://ieeexplore.ieee.org/document/8054694/

autoencoderfiber

This shows how to use Autoencoders for learning constellations and receivers in fiber optical communications

binning-for-mi-estimation

Program estimating the mutual information between two variables using binning. Plots MI vs. number of samples for varying numbers of bins. Can compare to MINE (Mutual Information Neural Estimator), presented in the paper by Belghazi.

bpcnn

capacity-approaching-autoencoders

Repository with the code on autoencoders and mutual information

capacity-estimation-on-the-mathworks-5g-nr-cdl-model

Single-link channel capacity estimation on the microwave and millimetre wave frequencies by using the Mathworks 5G NR CDL model for NLOS.

capacity-estimator-via-dine

capacity-functions

C / MATLAB functions to evaluate mutual information for optical communications

capacity-rl

capacity-rl-po

Policy optimization technique to compute the feedback capacity

carrier-frequency-offset

Detailed code used for researching machine learning for carrier frequency offset

ccmi

Classifier based mutual information, conditional mutual information estimation; conditional independence testing

channelcodingprojectlist

List of open source channel coding projects and libraries.

claude

End-to-end learning of optical communication systems

club

Code for ICML2020 paper - CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information

codec2

Open source speech codec designed for communications quality speech between 450 and 3200 bit/s. The main application is low bandwidth HF/VHF digital radio.

communication-oriented-autoencoders---where-shannon-meets-wiener

the python codes of paper "Communication-oriented Autoencoders - where Shannon meets Wiener"

comnet-ofdm

Implemention of ComNet

comparison_of_communication_autoencoder_mi_gan_wgan

Master Thesis compairing Communicationsystems Baised on GAN and baised on MI

complex_convolutions

2020 IEEE ICC: Open Workshop On Machine Learning In Communications.

compression

Data compression in TensorFlow

convolutionaneuralnetworkstoenhancecodedspeech

In this work we propose two postprocessing approaches applying convolutional neural networks (CNNs) either in the time domain or the cepstral domain to enhance the coded speech without any modification of the codecs. The time domain approach follows an end-to-end fashion, while the cepstral domain approach uses analysis-synthesis with cepstral domain features. The proposed postprocessors in both domains are evaluated for various narrowband and wideband speech codecs in a wide range of conditions. The proposed postprocessor improves speech quality (PESQ) by up to 0.25 MOS-LQO points for G.711, 0.30 points for G.726, 0.82 points for G.722, and 0.26 points for adaptive multirate wideband codec (AMR-WB). In a subjective CCR listening test, the proposed postprocessor on G.711-coded speech exceeds the speech quality of an ITU-T-standardized postfilter by 0.36 CMOS points, and obtains a clear preference of 1.77 CMOS points compared to G.711, even en par with uncoded speech.

cooperative-multi-agent-reinforcement-learning-for-low-level-wireless-communication

Spring 2017 Deep Reinforcement Learning Final Project

cryptogan

Final year project. A GAN based approach to encrypt communication between two symmetrically secure parties.

d2l-zh

《动手学深度学习》：面向中文读者、能运行、可讨论。英文版即伯克利“深度学习导论”教材。