公开(公告)号：US10769191B2

公开(公告)日：2020-09-08

申请号：US14576907

申请日：2014-12-19

Applicant: Google LLC

Inventor： Gregory Sean Corrado ,  Tomas Mikolov ,  Samy Bengio ,  Yoram Singer ,  Jonathon Shlens ,  Andrea L. Frome ,  Jeffrey Adgate Dean ,  Mohammad Norouzi

IPC: G06F16/30 ,  G06F16/35 ,  G06F16/50

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying data objects. One of the methods includes obtaining data that associates each term in a vocabulary of terms with a respective high-dimensional representation of the term; obtaining classification data for a data object, wherein the classification data includes a respective score for each of a plurality of categories, and wherein each of the categories is associated with a respective category label; computing an aggregate high-dimensional representation for the data object from high-dimensional representations for the category labels associated with the categories and the respective scores; identifying a first term in the vocabulary of terms having a high-dimensional representation that is closest to the aggregate high-dimensional representation; and selecting the first term as a category label for the data object.

公开(公告)号：US20200012905A1

公开(公告)日：2020-01-09

申请号：US16576321

申请日：2019-09-19

Applicant: Google LLC

Inventor： Samuel Bengio ,  Jeffrey Adgate Dean ,  Quoc V. Le ,  Jonathon Shlens ,  Yoram Singer

IPC: G06K9/72 ,  G06N20/00 ,  G06N7/00 ,  G06K9/00 ,  G06K9/62

Abstract: Systems and techniques are disclosed for labeling objects within an image. The objects may be labeled by selecting an option from a plurality of options such that each option is a potential label for the object. An option may have an option score associated with. Additionally, a relation score may be calculated for a first option and a second option corresponding to a second object in an image. The relation score may be based on a frequency, probability, or observance corresponding to the co-occurrence of text associated with the first option and the second option in a text corpus such as the World Wide Web. An option may be selected as a label for an object based on a global score calculated based at least on an option score and relation score associated with the option.

公开(公告)号：US10445623B2

公开(公告)日：2019-10-15

申请号：US15488041

申请日：2017-04-14

Applicant: Google LLC

Inventor： Samy Bengio ,  Jeffrey Adgate Dean ,  Quoc V. Le ,  Jonathon Shlens ,  Yoram Singer

IPC: G06K9/72 ,  G06N20/00 ,  G06N7/00 ,  G06K9/00 ,  G06K9/62

Abstract: Systems and techniques are disclosed for labeling objects within an image. The objects may be labeled by selecting an option from a plurality of options such that each option is a potential label for the object. An option may have an option score associated with. Additionally, a relation score may be calculated for a first option and a second option corresponding to a second object in an image. The relation score may be based on a frequency, probability, or observance corresponding to the co-occurrence of text associated with the first option and the second option in a text corpus such as the World Wide Web. An option may be selected as a label for an object based on a global score calculated based at least on an option score and relation score associated with the option.

公开(公告)号：US20240273410A1

公开(公告)日：2024-08-15

申请号：US18544347

申请日：2023-12-18

Applicant: Google LLC

Inventor： Jonathon Shlens ,  Quoc V. Le ,  Ekin Dogus Cubuk ,  Barret Zoph

IPC: G06N20/00 ,  G06F18/21 ,  G06F18/214 ,  G06N3/04 ,  G06N3/08

CPC classification number: G06N20/00 ,  G06F18/214 ,  G06F18/217 ,  G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a machine learning model. One of the methods includes obtaining a training data set for training a machine learning model, the training data set comprising a plurality of training inputs; determining a plurality of data augmentation policies, wherein each data augmentation policy defines a procedure for processing a training input to generate a transformed training input; for each data augmentation policy, training the machine learning model using the data augmentation policy; determining, for each data augmentation policy, a quality measure of the machine learning model that has been trained using the data augmentation policy; and selecting a final data augmentation policy based using the quality measures of the machine learning models.

公开(公告)号：US11790233B2

公开(公告)日：2023-10-17

申请号：US16915502

申请日：2020-06-29

Applicant: Google LLC

Inventor： Ian Goodfellow ,  Tianqi Chen ,  Jonathon Shlens

IPC: G06N3/08 ,  G06N3/04 ,  G06N3/082 ,  G06N3/045

CPC classification number: G06N3/082 ,  G06N3/04 ,  G06N3/045

Abstract: The specification describes methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a larger neural network from a smaller neural network. One of the described methods includes obtaining data specifying an original neural network and generating a larger neural network from the original neural network. The larger neural network has a larger neural network structure than the original neural network structure. The values of the parameters of the original neural network units and the additional neural network units are initialized so that the larger neural network generates the same outputs from the same inputs as the original neural network, and the larger neural network is trained to determine trained values of the parameters of the original neural network units and the additional neural network units from the initialized values.

公开(公告)号：US20220114400A1

公开(公告)日：2022-04-14

申请号：US17556871

申请日：2021-12-20

Applicant: Google LLC

Inventor： Jonathon Shlens ,  Quoc V. Le ,  Ekin Dogus Cubuk ,  Barret Zoph

IPC: G06K9/62 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a machine learning model. One of the methods includes obtaining a training data set for training a machine learning model, the training data set comprising a plurality of training inputs; determining a plurality of data augmentation policies, wherein each data augmentation policy defines a procedure for processing a training input to generate a transformed training input; for each data augmentation policy, training the machine learning model using the data augmentation policy; determining, for each data augmentation policy, a quality measure of the machine learning model that has been trained using the data augmentation policy; and selecting a final data augmentation policy based using the quality measures of the machine learning models.

公开(公告)号：US20210097348A1

公开(公告)日：2021-04-01

申请号：US16833449

申请日：2020-03-27

Applicant: Google LLC

Inventor： Jonathon Shlens ,  Quoc V. Le ,  Ekin Dogus Cubuk ,  Barret Zoph

IPC: G06K9/62 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a machine learning model. One of the methods includes obtaining a training data set for training a machine learning model, the training data set comprising a plurality of training inputs; determining a plurality of data augmentation policies, wherein each data augmentation policy defines a procedure for processing a training input to generate a transformed training input; for each data augmentation policy, training the machine learning model using the data augmentation policy; determining, for each data augmentation policy, a quality measure of the machine learning model that has been trained using the data augmentation policy; and selecting a final data augmentation policy based using the quality measures of the machine learning models.

公开(公告)号：US20200380023A1

公开(公告)日：2020-12-03

申请号：US16998891

申请日：2020-08-20

Applicant: Google LLC

Inventor： Gregory Sean Corrado ,  Tomas Mikolov ,  Samy Bengio ,  Yoram Singer ,  Jonathon Shlens ,  Andrea L. Frome ,  Jeffrey Adgate Dean ,  Mohammad Norouzi

IPC: G06F16/35 ,  G06F16/50

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying data objects. One of the methods includes obtaining data that associates each term in a vocabulary of terms with a respective high-dimensional representation of the term; obtaining classification data for a data object, wherein the classification data includes a respective score for each of a plurality of categories, and wherein each of the categories is associated with a respective category label; computing an aggregate high-dimensional representation for the data object from high-dimensional representations for the category labels associated with the categories and the respective scores; identifying a first term in the vocabulary of terms having a high-dimensional representation that is closest to the aggregate high-dimensional representation; and selecting the first term as a category label for the data object.

公开(公告)号：US20200065689A1

公开(公告)日：2020-02-27

申请号：US16674801

申请日：2019-11-05

Applicant: Google LLC

Inventor： Vijay Vasudevan ,  Barret Zoph ,  Jonathon Shlens ,  Quoc V. Le

IPC: G06N5/04 ,  G06N3/04 ,  G06N3/08 ,  G06T7/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining neural network architectures. One of the methods includes generating, using a controller neural network having controller parameters and in accordance with current values of the controller parameters, a batch of output sequences. The method includes, for each output sequence in the batch: generating an instance of a child convolutional neural network (CNN) that includes multiple instances of a first convolutional cell having an architecture defined by the output sequence; training the instance of the child CNN to perform an image processing task; and evaluating a performance of the trained instance of the child CNN on the task to determine a performance metric for the trained instance of the child CNN; and using the performance metrics for the trained instances of the child CNN to adjust current values of the controller parameters of the controller neural network.

公开(公告)号：US10535164B2

公开(公告)日：2020-01-14

申请号：US16380010

申请日：2019-04-10

Applicant: Google LLC

Inventor： Jonathon Shlens ,  Vincent Dumoulin ,  Manjunath Kudlur Venkatakrishna

IPC: G06N3/08 ,  G06N3/04 ,  G06T11/00 ,  G06K9/62

Abstract: A method for applying a style to an input image to generate a stylized image. The method includes maintaining data specifying respective parameter values for each image style in a set of image styles, receiving an input including an input image and data identifying an input style to be applied to the input image to generate a stylized image that is in the input style, determining, from the maintained data, parameter values for the input style, and generating the stylized image by processing the input image using a style transfer neural network that is configured to process the input image to generate the stylized image.