公开(公告)号：US10521729B2

公开(公告)日：2019-12-31

申请号：US16040067

申请日：2018-07-19

Applicant: Google LLC

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

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

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：US20190026639A1

公开(公告)日：2019-01-24

申请号：US16040067

申请日：2018-07-19

Applicant: Google LLC

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

IPC: G06N5/04 ,  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：US11774596B2

公开(公告)日：2023-10-03

申请号：US17901224

申请日：2022-09-01

Applicant: Google LLC

Inventor： Jonathon Shlens ,  Vijay Vasudevan ,  Jiquan Ngiam ,  Wei Han ,  Zhifeng Chen ,  Brandon Chauloon Yang ,  Benjamin James Caine ,  Zhengdong Zhang ,  Christoph Sprunk ,  Ouais Alsharif ,  Junhua Mao ,  Chen Wu

IPC: G01S17/89 ,  G06T17/00 ,  G06V20/10 ,  G06N3/048 ,  G06V10/764 ,  G06V20/56

CPC classification number: G01S17/89 ,  G06N3/048 ,  G06T17/00 ,  G06V10/764 ,  G06V20/10 ,  G06V20/56

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing data generated by a sensing system that rotationally senses an environment. In one aspect, a method comprises partitioning a predetermined period of time into a plurality of sub-periods, wherein the predetermined period of time is a period of time for which data generated by the sensing system constitutes a complete rotational sensing of the environment; for each sub-period: receiving current data generated by the sensing system during the sub-period and characterizing a respective partial scene of the environment; processing the current data using an object detection neural network to generate a current object detection output that is specific to the respective partial scene of the environment.

公开(公告)号：US11651259B2

公开(公告)日：2023-05-16

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 ,  G06N5/046

CPC classification number: G06N5/046 ,  G06N3/0445 ,  G06N3/0454 ,  G06N3/08 ,  G06T7/0002 ,  G06T2207/20084

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：US20220215654A1

公开(公告)日：2022-07-07

申请号：US17606976

申请日：2020-05-22

Applicant: Google LLC

Inventor： Jonathon Shlens ,  Ashish Teku Vaswani ,  Niki J. Parmar ,  Prajit Ramachandran ,  Anselm Caelifer Levskaya ,  Irwan Bello

IPC: G06V10/82 ,  G06N3/04 ,  G06T9/00

Abstract: A system implemented as computer programs on one or more computers in one or more locations that implements a computer vision model is described. The computer vision model includes a positional local self-attention layer that is configured to receive an input feature map and to generate an output feature map. For each input element in the input feature map, the positional local self-attention layer generates a respective output element for the output feature map by generating a memory block including neighboring input elements around the input element, generates a query vector using the input element and a query weight matrix, for each neighboring element in the memory block, performs positional local self-attention operations to generate a temporary output element, and generates the respective output element by summing temporary output elements of the neighboring elements in the memory block.

公开(公告)号：US20210081796A1

公开(公告)日：2021-03-18

申请号：US17107745

申请日：2020-11-30

Applicant: Google LLC

Inventor： Barret Zoph ,  Jonathon Shlens ,  Yukun Zhu ,  Maxwell Donald Collins ,  Liang-Chieh Chen ,  Gerhard Florian Schroff ,  Hartwig Adam ,  Georgios Papandreou

IPC: G06N3/08 ,  G06N20/00 ,  G06F17/15 ,  G06K9/62 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining neural network architectures. One of the methods includes obtaining training data for a dense image prediction task; and determining an architecture for a neural network configured to perform the dense image prediction task, comprising: searching a space of candidate architectures to identify one or more best performing architectures using the training data, wherein each candidate architecture in the space of candidate architectures comprises (i) the same first neural network backbone that is configured to receive an input image and to process the input image to generate a plurality of feature maps and (ii) a different dense prediction cell configured to process the plurality of feature maps and to generate an output for the dense image prediction task; and determining the architecture for the neural network based on the best performing candidate architectures.

公开(公告)号：US10853726B2

公开(公告)日：2020-12-01

申请号：US16425900

申请日：2019-05-29

Applicant: Google LLC

Inventor： Barret Zoph ,  Jonathon Shlens ,  Yukun Zhu ,  Maxwell Donald Emmet Collins ,  Liang-Chieh Chen ,  Gerhard Florian Schroff ,  Hartwig Adam ,  Georgios Papandreou

IPC: G06N3/08 ,  G06N20/00 ,  G06F17/15 ,  G06K9/62 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining neural network architectures. One of the methods includes obtaining training data for a dense image prediction task; and determining an architecture for a neural network configured to perform the dense image prediction task, comprising: searching a space of candidate architectures to identify one or more best performing architectures using the training data, wherein each candidate architecture in the space of candidate architectures comprises (i) the same first neural network backbone that is configured to receive an input image and to process the input image to generate a plurality of feature maps and (ii) a different dense prediction cell configured to process the plurality of feature maps and to generate an output for the dense image prediction task; and determining the architecture for the neural network based on the best performing candidate architectures.

公开(公告)号：US20190236814A1

公开(公告)日：2019-08-01

申请号：US16380010

申请日：2019-04-10

Applicant: Google LLC

Inventor： Jonathon Shlens ,  Vincent Dumoulin ,  Manjunath Kudlur Venkatakrishna

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

CPC classification number: G06T11/001 ,  G06K9/6253 ,  G06K9/6256 ,  G06N3/04 ,  G06N3/08 ,  G06T11/00

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.

公开(公告)号：US10127475B1

公开(公告)日：2018-11-13

申请号：US15273572

申请日：2016-09-22

Applicant: Google LLC

Inventor： Gregory S. Corrado ,  Jeffrey A. Dean ,  Samy Bengio ,  Andrea L. Frome ,  Jonathon Shlens

IPC: G06K9/62

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying images. One of the methods includes obtaining data that associates each of a plurality of object category labels with a respective high-dimensional representation of the object category label, wherein the high-dimensional representation of the object category label is a numeric representation of the object category label in a high-dimensional space; receiving an input image; processing the input image using one or more core layers to generate an alternative representation of the input image; processing the alternative representation of the input image using a transformation layer to determine a high-dimensional representation for the input image; selecting, from the high-dimensional representations associated with the object category labels, a closest high-dimensional representation to the high-dimensional representation for the input image; and selecting the category label associated with the closest high-dimensional representation as a predicted label for the input image.

公开(公告)号：US20240220527A1

公开(公告)日：2024-07-04

申请号：US18606458

申请日：2024-03-15

Applicant: Google LLC

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

IPC: G06F16/35 ,  G06F16/50

CPC classification number: 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.