Updated title to include timeline.
Will the first published 6G specification include the use of "AI" in the physical layer?
This means that some part of the physical layer specification assumes the use of data-driven learned algorithms and makes provision for same. Note that there could still be alternative provision for non-AI approaches for certain deployments or in fallback scenarios.
This could include removal of pilots on the assumption that the channel state can be inferred, removal of cyclic prefix on the basis that interference can be mitigated by deep learning techniques, anything involving an auto encoder architecture which spans base station and user equipment, etc.
The 3GPP spec must include this; it's not sufficient for specific implementations to use deep learning to which the spec is agnostic.
The phy is everything from the ADC/DACs through to decoded bits.
Closes when corresponding 3GPP spec is published, expected in rel19 end 2025.
For a longer timeline, see
1,000Opus has production-ready deep-learning-based redundancy, called DRED, today: https://opus-codec.org/demo/opus-1.5/
It runs on phones and uses of phones made in the past 5 years are not expected to notice the overhead.
A similar redundancy implementation would be beneficial for radio transmissions that encounter a lot of noise. Based on this, I think this market is undervalued.
I want to add the following clarification to the description:
"Note that there could still be alternative provision for non-AI approaches for certain deployments or in fallback scenarios."
But before doing so, I'll allow 24h for objections. Note I've already sold my (10M) bet at a loss and have no stake at the moment.