US 12,462,160 B2
Performing distributed processing using layers of a neural network divided between a first device and a second device
Ryo Takahashi, Tokyo (JP); and Yukio Oobuchi, Kanagawa (JP)
Assigned to Sony Corporation, Tokyo (JP)
Appl. No. 17/263,868
Filed by Sony Corporation, Tokyo (JP)
PCT Filed Jul. 10, 2019, PCT No. PCT/JP2019/027415
§ 371(c)(1), (2) Date Jan. 27, 2021,
PCT Pub. No. WO2020/026741, PCT Pub. Date Feb. 6, 2020.
Claims priority of application No. 2018-147180 (JP), filed on Aug. 3, 2018.
Prior Publication US 2021/0312295 A1, Oct. 7, 2021
Int. Cl. G06F 18/21 (2023.01); G06N 3/086 (2023.01); G06N 3/048 (2023.01)
CPC G06N 3/086 (2013.01) [G06F 18/2163 (2023.01); G06F 18/217 (2023.01); G06N 3/048 (2023.01)] 11 Claims
OG exemplary drawing
 
1. An information processing method executed by processing circuitry, the method comprising:
evaluating transfer of information between layers of a neural network performing distributed processing, wherein the layers of the neural network are divided between a first device and a second device, to determine an evaluation value;
wherein:
a third layer among the layers of the neural network that lies in a portion deeper than a second layer from which second information having a maximum size is output, the third layer outputs third information having a size smaller than that of first information output from an input layer of the neural network, the third layer is determined to be a transfer point at which the third information is to be transmitted from the first device to the second device, and
the neural network is evaluated based on the third information on the determined transfer point;
determining if the evaluation value meets a predetermined condition;
determining a structure of the neural network that meets the predetermined condition; and
executing a distributed process using the determined structure in which the layers of the neural network are divided between the first device and the second device.