公开(公告)号：US20240127058A1

公开(公告)日：2024-04-18

申请号：US18471404

申请日：2023-09-21

Applicant: Google LLC

Inventor： Mohammad Norouzi ,  Daniel Aaron Abolafia ,  Quoc V. Le

IPC: G06N3/08 ,  G06N3/044

CPC classification number: G06N3/08 ,  G06N3/044

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network using a priority queue. One of the methods includes maintaining data identifying a set of K output sequences that were previously generated; selecting at least one of the output sequences from the set of output sequences; for each selected output sequence, determining a respective score; determining, for each selected sequence, a respective first update to the current values of the controller parameters; generating a batch of new output sequences using the controller neural network; obtaining a respective reward for each of the new output sequences; determining, from the new output sequences and the output sequences in the maintained data, the K output sequences that have the highest rewards; and modifying the maintained data.

公开(公告)号：US11797839B2

公开(公告)日：2023-10-24

申请号：US16174126

申请日：2018-10-29

Applicant: Google LLC

Inventor： Mohammad Norouzi ,  Daniel Aaron Abolafia ,  Quoc V. Le

IPC: G06N3/08 ,  G06N3/04 ,  G06N3/044

CPC classification number: G06N3/08 ,  G06N3/044

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network using a priority queue. One of the methods includes maintaining data identifying a set of K output sequences that were previously generated; selecting at least one of the output sequences from the set of output sequences; for each selected output sequence, determining a respective score; determining, for each selected sequence, a respective first update to the current values of the controller parameters; generating a batch of new output sequences using the controller neural network; obtaining a respective reward for each of the new output sequences; determining, from the new output sequences and the output sequences in the maintained data, the K output sequences that have the highest rewards; and modifying the maintained data.

公开(公告)号：US20190130267A1

公开(公告)日：2019-05-02

申请号：US16174126

申请日：2018-10-29

Applicant: Google LLC

Inventor： Mohammad Norouzi ,  Daniel Aaron Abolafia ,  Quoc V. Le

IPC: G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network using a priority queue. One of the methods includes maintaining data identifying a set of K output sequences that were previously generated; selecting at least one of the output sequences from the set of output sequences; for each selected output sequence, determining a respective score; determining, for each selected sequence, a respective first update to the current values of the controller parameters; generating a batch of new output sequences using the controller neural network; obtaining a respective reward for each of the new output sequences; determining, from the new output sequences and the output sequences in the maintained data, the K output sequences that have the highest rewards; and modifying the maintained data.