US 11,984,955 B2
Configurable neural network for channel state feedback (CSF) learning
Bo Chen, Beijing (CN); Pavan Kumar Vitthaladevuni, San Diego, CA (US); Taesang Yoo, San Diego, CA (US); Naga Bhushan, San Diego, CA (US); Jay Kumar Sundararajan, San Diego, CA (US); Ruifeng Ma, Beijing (CN); June Namgoong, San Diego, CA (US); Krishna Kiran Mukkavilli, San Diego, CA (US); Hao Xu, Beijing (CN); and Tingfang Ji, San Diego, CA (US)
Assigned to QUALCOMM Incorporated, San Diego, CA (US)
Appl. No. 17/801,505
Filed by QUALCOMM Incorporated, San Diego, CA (US)
PCT Filed Apr. 17, 2020, PCT No. PCT/CN2020/085301
§ 371(c)(1), (2) Date Aug. 22, 2022,
PCT Pub. No. WO2021/208061, PCT Pub. Date Oct. 21, 2021.
Prior Publication US 2023/0084164 A1, Mar. 16, 2023
Int. Cl. H04B 7/06 (2006.01)
CPC H04B 7/0626 (2013.01) [H04B 7/0695 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method of wireless communication, by a user equipment (UE), comprising:
receiving a plurality of neural network training configurations for channel state feedback (CSF), each configuration corresponding to a different neural network framework;
training each of a plurality neural network decoder-encoder pairs in accordance with the received training configurations; and
receiving a message indicating/activating/deactivating a quantity of neural network pairs to be trained and which neural network pair to use for a specific channel state information (CSI) quantity.