For anyone interested in Autoencoders,
I can recommend chapter 17 of "hands on machine learning with sckit"
ISBN 978-1-492-03264-9
or
David you might be able to recommend a good online , accessable source ?
the following can provide some good starting points :
https://medium.com/search?q=understanding+autoencoders+
<https://medium.com/search?q=understanding+autoencoders+>
maybe:
https://medium.com/data-science/understanding-autoencoders-with-an-example-a-step-by-step-tutorial-693c3a4e9836
<https://medium.com/data-science/understanding-autoencoders-with-an-example-a-step-by-step-tutorial-693c3a4e9836>
For medium which I subscribe/donate to, non subs can access a small
number of articles free
On 17/08/2025 06:59, david wrote:
Hi Glen,
Yes indeed it can be trained to any channel you like. We've been doing
some work for the VHF/UHF land mobile radio (LMR) space where it's
trained to pass through analog FM radios (see freedv.org blog posts,
search on BBFM).
Greg - I suspect the final form of this technology arc will be
something like you suggest, resulting in high quality speech at very
low SNRs. Current work on RADE V2 has the ML doing the sync (e.g.
equalisation for the HF channel, fine timing, frame sync) rather than
_______________________________________________
Freetel-codec2 mailing list
Freetel-codec2@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/freetel-codec2
