US 12,355,633 B2
Configuring a user equipment for machine learning
Xipeng Zhu, San Diego, CA (US); Gavin Bernard Horn, La Jolla, CA (US); Vanitha Aravamudhan Kumar, San Diego, CA (US); Vishal Dalmiya, San Diego, CA (US); Shankar Krishnan, San Diego, CA (US); Rajeev Kumar, San Diego, CA (US); Taesang Yoo, San Diego, CA (US); Eren Balevi, Brooklyn, NY (US); Aziz Gholmieh, Del Mar, CA (US); and Rajat Prakash, San Diego, CA (US)
Assigned to QUALCOMM Incorporated, San Diego, CA (US)
Filed by QUALCOMM Incorporated, San Diego, CA (US)
Filed on Jan. 18, 2024, as Appl. No. 18/415,896.
Application 18/415,896 is a continuation of application No. 17/467,156, filed on Sep. 3, 2021, granted, now 11,916,754.
Prior Publication US 2024/0223465 A1, Jul. 4, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. H04L 41/16 (2022.01); H04L 41/0803 (2022.01); H04W 88/08 (2009.01); G06N 20/00 (2019.01)
CPC H04L 41/16 (2013.01) [H04L 41/0803 (2013.01); H04W 88/08 (2013.01); G06N 20/00 (2019.01)] 22 Claims
OG exemplary drawing
 
1. A user equipment (UE), comprising:
one or more memories storing processor-executable code; and
one or more processors coupled with the one or more memories and individually or collectively operable to execute the code to cause the UE to:
transmit capability information that corresponds to one or more neural network functions, one or more machine learning models, or any combination thereof; and
receive a machine learning configuration corresponding to a neural network function of the one or more neural network functions or a machine learning model of the one or more machine learning models, wherein:
the machine learning configuration corresponding to the one or more neural network functions is based at least in part on the capability information, and
the one or more machine learning models, the one or more neural network functions, or any combination thereof are associated with a machine learning model repository that is included in or coupled with a network entity,
wherein, the neural network function or the machine learning model is to be activated based on an associated activation function.