Authors :
Anjana P K; Ameenudeen P E
Volume/Issue :
Volume 9 - 2024, Issue 1 - January
Google Scholar :
http://tinyurl.com/24wk7252
Scribd :
http://tinyurl.com/3m2wf4vx
DOI :
https://doi.org/10.5281/zenodo.10629098
Abstract :
To demonstrate over the air transmission, it is
essential to frame, alternate and execute a transmission
systems repressed by neural networks. Autoencoders are
used to train the entire system composed of transmitters
and receivers. Estab- lishing a vital novel style of
thinking regarding communications network design as a
point to point regeneration task that seeks to optimise Tx
and Rx systems into a single process by interpreting a
transmission system as an autoencoder is performed.
In this, several autoencoders such as deep encoder,
convolutional autoencoder and a simplest possible
autoencoder is simulated in Python. Lastly, BLER
versus Eb/N0 for the (2,2) and (7,4) autoencoder is
plotted.
Keywords :
Autoencoder, Deep Learning, End-to-End Communication.
To demonstrate over the air transmission, it is
essential to frame, alternate and execute a transmission
systems repressed by neural networks. Autoencoders are
used to train the entire system composed of transmitters
and receivers. Estab- lishing a vital novel style of
thinking regarding communications network design as a
point to point regeneration task that seeks to optimise Tx
and Rx systems into a single process by interpreting a
transmission system as an autoencoder is performed.
In this, several autoencoders such as deep encoder,
convolutional autoencoder and a simplest possible
autoencoder is simulated in Python. Lastly, BLER
versus Eb/N0 for the (2,2) and (7,4) autoencoder is
plotted.
Keywords :
Autoencoder, Deep Learning, End-to-End Communication.
