Search International and National Patent Collections

1. (WO2018222299) DYNAMIC TASK ALLOCATION FOR NEURAL NETWORKS

Pub. No.:    WO/2018/222299    International Application No.:    PCT/US2018/029201
Publication Date: Fri Dec 07 00:59:59 CET 2018 International Filing Date: Wed Apr 25 01:59:59 CEST 2018
IPC: G06F 9/50
G06N 3/063
Applicants: APPLE INC.
Inventors: ROSSI, Francesco
KAPOOR, Gaurav
SIRACUSA, Michael R.
MARCH, William B.
Title: DYNAMIC TASK ALLOCATION FOR NEURAL NETWORKS
Abstract:
The subject technology provides for dynamic task allocation for neural network models. The subject technology determines an operation performed at a node of a neural network model. The subject technology assigns an annotation to indicate whether the operation is better performed on a CPU or a GPU based at least in part on hardware capabilities of a target platform. The subject technology determines whether the neural network model includes a second layer. The subject technology, in response to determining that the neural network model includes a second layer, for each node of the second layer of the neural network model, determines a second operation performed at the node. Further the subject technology assigns a second annotation to indicate whether the second operation is better performed on the CPU or the GPU based at least in part on the hardware capabilities of the target platform.