公开(公告)号：US10699186B2

公开(公告)日：2020-06-30

申请号：US14956699

申请日：2015-12-02

Applicant: Google Inc.

Inventor： Warren Craddock ,  Fabien Viger

IPC: G06N3/063 ,  G06N3/04

Abstract: Systems and methods are provided for determining an order of execution of a neural network. For instance, data indicative of a neural network and data indicative of an amount of available memory in a constrained memory space can be obtained. The neural network can include a plurality of operators. An order of execution associated with the neural network can then be determined. The order of execution specifies an order in which to execute each of the plurality of operators. The order of execution is determined based at least in part on the available memory in the constrained memory space. In particular, one or more graph search algorithms can be performed on a graph that is representative of the neural network to obtain the order of execution.

公开(公告)号：US20170161604A1

公开(公告)日：2017-06-08

申请号：US14956699

申请日：2015-12-02

Applicant: Google Inc.

Inventor： Warren Craddock ,  Fabien Viger

IPC: G06N3/08

Abstract: Systems and methods are provided for determining an order of execution of a neural network. For instance, data indicative of a neural network and data indicative of an amount of available memory in a constrained memory space can be obtained. The neural network can include a plurality of operators. An order of execution associated with the neural network can then be determined. The order of execution specifies an order in which to execute each of the plurality of operators. The order of execution is determined based at least in part on the available memory in the constrained memory space. In particular, one or more graph search algorithms can be performed on a graph that is representative of the neural network to obtain the order of execution.