公开(公告)号：US20240249138A1

公开(公告)日：2024-07-25

申请号：US18395282

申请日：2023-12-22

Applicant: Google LLC

Inventor： Sergey Ioffe ,  Corinna Cortes

IPC: G06N3/08 ,  G06F18/10 ,  G06F18/2415 ,  G06N3/04 ,  G06N3/084 ,  G06V10/70 ,  G06V10/82

CPC classification number: G06N3/08 ,  G06F18/10 ,  G06F18/2415 ,  G06N3/04 ,  G06N3/084 ,  G06V10/70 ,  G06V10/82 ,  G06T2207/20081

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images or features of images using an image classification system that includes a batch normalization layer. One of the systems includes a convolutional neural network configured to receive an input comprising an image or image features of the image and to generate a network output that includes respective scores for each object category in a set of object categories, the score for each object category representing a likelihood that that the image contains an image of an object belonging to the category, and the convolutional neural network comprising: a plurality of neural network layers, the plurality of neural network layers comprising a first convolutional neural network layer and a second neural network layer; and a batch normalization layer between the first convolutional neural network layer and the second neural network layer.

公开(公告)号：US20250013864A1

公开(公告)日：2025-01-09

申请号：US18740393

申请日：2024-06-11

Applicant: Google LLC

Inventor： Sergey Ioffe ,  Corinna Cortes

IPC: G06N3/08 ,  G06F18/2415 ,  G06N3/04 ,  G06N3/084 ,  G06V10/70 ,  G06V10/82

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using a neural network system that includes a batch normalization layer. One of the methods includes receiving a respective first layer output for each training example in the batch; computing a plurality of normalization statistics for the batch from the first layer outputs; normalizing each component of each first layer output using the normalization statistics to generate a respective normalized layer output for each training example in the batch; generating a respective batch normalization layer output for each of the training examples from the normalized layer outputs; and providing the batch normalization layer output as an input to the second neural network layer.

公开(公告)号：US20200234127A1

公开(公告)日：2020-07-23

申请号：US16837959

申请日：2020-04-01

Applicant: Google LLC

Inventor： Sergey Ioffe ,  Corinna Cortes

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images or features of images using an image classification system that includes a batch normalization layer. One of the systems includes a convolutional neural network configured to receive an input comprising an image or image features of the image and to generate a network output that includes respective scores for each object category in a set of object categories, the score for each object category representing a likelihood that that the image contains an image of an object belonging to the category, and the convolutional neural network comprising: a plurality of neural network layers, the plurality of neural network layers comprising a first convolutional neural network layer and a second neural network layer; and a batch normalization layer between the first convolutional neural network layer and the second neural network layer.

公开(公告)号：US20200057924A1

公开(公告)日：2020-02-20

申请号：US16226483

申请日：2018-12-19

Applicant: Google LLC

Inventor： Sergey Ioffe ,  Corinna Cortes

IPC: G06K9/62 ,  G06N3/04 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images or features of images using an image classification system that includes a batch normalization layer. One of the systems includes a convolutional neural network configured to receive an input comprising an image or image features of the image and to generate a network output that includes respective scores for each object category in a set of object categories, the score for each object category representing a likelihood that that the image contains an image of an object belonging to the category, and the convolutional neural network comprising: a plurality of neural network layers, the plurality of neural network layers comprising a first convolutional neural network layer and a second neural network layer; and a batch normalization layer between the first convolutional neural network layer and the second neural network layer.

公开(公告)号：US20210224653A1

公开(公告)日：2021-07-22

申请号：US17156453

申请日：2021-01-22

Applicant: Google LLC

Inventor： Sergey Ioffe ,  Corinna Cortes

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using a neural network system that includes a batch normalization layer. One of the methods includes receiving a respective first layer output for each training example in the batch; computing a plurality of normalization statistics for the batch from the first layer outputs; normalizing each component of each first layer output using the normalization statistics to generate a respective normalized layer output for each training example in the batch; generating a respective batch normalization layer output for each of the training examples from the normalized layer outputs; and providing the batch normalization layer output as an input to the second neural network layer.

公开(公告)号：US20200012942A1

公开(公告)日：2020-01-09

申请号：US16572454

申请日：2019-09-16

Applicant: Google LLC

Inventor： Sergey Ioffe ,  Corinna Cortes

IPC: G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using a neural network system that includes a batch normalization layer. One of the methods includes receiving a respective first layer output for each training example in the batch; computing a plurality of normalization statistics for the batch from the first layer outputs; normalizing each component of each first layer output using the normalization statistics to generate a respective normalized layer output for each training example in the batch; generating a respective batch normalization layer output for each of the training examples from the normalized layer outputs; and providing the batch normalization layer output as an input to the second neural network layer.

公开(公告)号：US12033073B2

公开(公告)日：2024-07-09

申请号：US17156464

申请日：2021-01-22

Applicant: Google LLC

Inventor： Sergey Ioffe ,  Corinna Cortes

IPC: G06N3/08 ,  G06F18/10 ,  G06F18/2415 ,  G06N3/04 ,  G06N3/084 ,  G06V10/70 ,  G06V10/82

CPC classification number: G06N3/08 ,  G06F18/10 ,  G06F18/2415 ,  G06N3/04 ,  G06N3/084 ,  G06V10/70 ,  G06V10/82 ,  G06T2207/20081

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using a neural network system that includes a batch normalization layer. One of the methods includes receiving a respective first layer output for each training example in the batch; computing a plurality of normalization statistics for the batch from the first layer outputs; normalizing each component of each first layer output using the normalization statistics to generate a respective normalized layer output for each training example in the batch; generating a respective batch normalization layer output for each of the training examples from the normalized layer outputs; and providing the batch normalization layer output as an input to the second neural network layer.

公开(公告)号：US11853885B2

公开(公告)日：2023-12-26

申请号：US17723007

申请日：2022-04-18

Applicant: Google LLC

Inventor： Sergey Ioffe ,  Corinna Cortes

IPC: G06V10/82 ,  G06N3/08 ,  G06N3/04 ,  G06N3/084 ,  G06F18/10 ,  G06F18/2415 ,  G06V10/70

CPC classification number: G06N3/08 ,  G06F18/10 ,  G06F18/2415 ,  G06N3/04 ,  G06N3/084 ,  G06V10/70 ,  G06V10/82 ,  G06T2207/20081

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images or features of images using an image classification system that includes a batch normalization layer. One of the systems includes a convolutional neural network configured to receive an input comprising an image or image features of the image and to generate a network output that includes respective scores for each object category in a set of object categories, the score for each object category representing a likelihood that that the image contains an image of an object belonging to the category, and the convolutional neural network comprising: a plurality of neural network layers, the plurality of neural network layers comprising a first convolutional neural network layer and a second neural network layer; and a batch normalization layer between the first convolutional neural network layer and the second neural network layer.

公开(公告)号：US11281973B2

公开(公告)日：2022-03-22

申请号：US17390768

申请日：2021-07-30

Applicant: Google LLC

Inventor： Sergey Ioffe ,  Corinna Cortes

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using a neural network system that includes a batch normalization layer. One of the methods includes receiving a respective first layer output for each training example in the batch; computing a plurality of normalization statistics for the batch from the first layer outputs; normalizing each component of each first layer output using the normalization statistics to generate a respective normalized layer output for each training example in the batch; generating a respective batch normalization layer output for each of the training examples from the normalized layer outputs; and providing the batch normalization layer output as an input to the second neural network layer.

公开(公告)号：US20210216870A1

公开(公告)日：2021-07-15

申请号：US17156464

申请日：2021-01-22

Applicant: Google LLC

Inventor： Sergey Ioffe ,  Corinna Cortes

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using a neural network system that includes a batch normalization layer. One of the methods includes receiving a respective first layer output for each training example in the batch; computing a plurality of normalization statistics for the batch from the first layer outputs; normalizing each component of each first layer output using the normalization statistics to generate a respective normalized layer output for each training example in the batch; generating a respective batch normalization layer output for each of the training examples from the normalized layer outputs; and providing the batch normalization layer output as an input to the second neural network layer.