	US 12,236,348 B2
	Deep neural network processing for a user equipment-coordination set
Jibing Wang, San Jose, CA (US); and Erik Richard Stauffer, Sunnyvale, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on May 16, 2024, as Appl. No. 18/666,539.
Application 18/666,539 is a division of application No. 18/306,010, filed on Apr. 24, 2023, granted, now 12,020,158.
Application 18/306,010 is a division of application No. 16/915,909, filed on Jun. 29, 2020, granted, now 11,663,472, issued on May 30, 2023.
Prior Publication US 2024/0303490 A1, Sep. 12, 2024
Int. Cl. G06F 3/08 (2006.01); G06N 3/04 (2023.01); G06N 3/08 (2023.01); H04B 7/026 (2017.01)

CPC G06N 3/08 (2013.01) [G06N 3/04 (2013.01); H04B 7/026 (2013.01)]

20 Claims

10. A coordinating user equipment (UE) comprising:

at least one processor; and

computer-readable storage media comprising instructions that, responsive to execution by the at least one processor, direct the coordinating UE to:

confirm, with a network entity, a training schedule that indicates a time period to fixedly maintain at least a first portion of an end-to-end (E2E) machine-learning (ML)

configuration that forms a first set of sub-deep neural network (DNN)s of an E2E DNN; and

determine, based on the training schedule, an adjustment to the first portion of the E2E ML configuration; and

direct one or more additional UEs participating in a user equipment-coordinated set (UECS) to update one or more sub-DNNs of the first set of sub-DNNs using the adjustment to the first portion of the E2E ML configuration.