US 12,001,943 B2
Communicating a neural network formation configuration
Jibing Wang, San Jose, CA (US); and Erik Richard Stauffer, Sunnyvale, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Appl. No. 16/962,497
Filed by Google LLC, Mountain View, CA (US)
PCT Filed Aug. 14, 2019, PCT No. PCT/US2019/046546
§ 371(c)(1), (2) Date Jul. 15, 2020,
PCT Pub. No. WO2021/029891, PCT Pub. Date Feb. 18, 2021.
Prior Publication US 2021/0049451 A1, Feb. 18, 2021
Int. Cl. H04W 24/02 (2009.01); G06N 3/045 (2023.01); G06N 3/063 (2023.01); H04W 4/06 (2009.01); H04W 8/24 (2009.01)
CPC G06N 3/063 (2013.01) [G06N 3/045 (2023.01); H04W 4/06 (2013.01); H04W 8/245 (2013.01); H04W 24/02 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method performed by a network entity associated with a wireless communication system, the method comprising:
transmitting, to a user equipment, a neural network table that includes a plurality of neural network formation configuration elements;
selecting one or more neural network formation configuration elements from the plurality of neural network formation configuration elements to create a first neural network formation configuration;
transmitting, to the user equipment, a first indication to direct the user equipment to form a first deep neural network using the first neural network formation configuration and to process control channel communications using the first deep neural network;
determining a second neural network formation configuration; and
transmitting, to the user equipment, a second indication to direct the user equipment to form a second deep neural network using the second neural network formation configuration and to process data channel communications transmitted over the wireless communication system using the second deep neural network.