US 11,929,853 B2
Data-driven probabilistic modeling of wireless channels using conditional variational auto-encoders
Arash Behboodi, Amsterdam (NL); Simeng Zheng, San Diego, CA (US); Joseph Binamira Soriaga, San Diego, CA (US); Max Welling, Bussum (NL); and Tribhuvanesh Orekondy, Diemen (NL)
Assigned to QUALCOMM Incorporated, San Diego, CA (US)
Filed by QUALCOMM Incorporated, San Diego, CA (US)
Filed on Oct. 18, 2021, as Appl. No. 17/504,341.
Claims priority of provisional application 63/093,728, filed on Oct. 19, 2020.
Prior Publication US 2022/0123966 A1, Apr. 21, 2022
Int. Cl. H04L 23/02 (2006.01); H04B 17/391 (2015.01); H04L 25/02 (2006.01); H04L 25/03 (2006.01)
CPC H04L 25/0254 (2013.01) [H04B 17/3912 (2015.01); H04B 17/3913 (2015.01); H04L 25/03165 (2013.01)] 40 Claims
OG exemplary drawing
 
1. A computer-implemented method using an artificial neural network comprising:
determining a conditional probability distribution representing a wireless communication channel based on a data set of transmit and receive sequences associated with one or more wireless communication node;
determining a latent representation of the wireless communication channel based on the conditional probability distribution; and
performing a channel-based function based on the latent representation.