公开(公告)号：US20200279134A1

公开(公告)日：2020-09-03

申请号：US16649599

申请日：2018-09-20

Applicant: GOOGLE LLC

Inventor： Konstantinos Bousmalis ,  Alexander Irpan ,  Paul Wohlhart ,  Yunfei Bai ,  Mrinal Kalakrishnan ,  Julian Ibarz ,  Sergey Vladimir Levine ,  Kurt Konolige ,  Vincent O. Vanhoucke ,  Matthew Laurance Kelcey

IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04 ,  B25J9/16

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training an action selection neural network that is used to control a robotic agent interacting with a real-world environment.

公开(公告)号：US10387531B1

公开(公告)日：2019-08-20

申请号：US14829525

申请日：2015-08-18

Applicant: Google LLC

Inventor： Vincent O. Vanhoucke

IPC: G06F16/958 ,  G06F17/24 ,  G06N3/04 ,  G06K9/00

Abstract: Structured documents are processed using convolutional neural networks. One of the methods includes receiving a rendered form of a structured document; mapping a grid of cells to the rendered form; assigning a respective numeric embedding to each cell in the grid, comprising, for each cell: identifying content in the structured document that corresponds to a portion of the rendered form that is mapped to the cell, mapping the identified content to a numeric embedding for the identified content, and assigning the numeric embedding for the identified content to the cell; generating a matrix representation of the structured document from the numeric embeddings assigned to the cells of the grids; and generating neural network features of the structured document by processing the matrix representation of the structured document through a subnetwork comprising one or more convolutional neural network layers.

公开(公告)号：US12073823B2

公开(公告)日：2024-08-27

申请号：US18506540

申请日：2023-11-10

Applicant: Google LLC

Inventor： Georg Heigold ,  Erik Mcdermott ,  Vincent O. Vanhoucke ,  Andrew W. Senior ,  Michiel A. U. Bacchiani

IPC: G10L15/06 ,  G06N3/045 ,  G10L15/16 ,  G10L15/183

CPC classification number: G10L15/063 ,  G06N3/045 ,  G10L15/16 ,  G10L15/183

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, by a first sequence-training speech model, a first batch of training frames that represent speech features of first training utterances; obtaining, by the first sequence-training speech model, one or more first neural network parameters; determining, by the first sequence-training speech model, one or more optimized first neural network parameters based on (i) the first batch of training frames and (ii) the one or more first neural network parameters; obtaining, by a second sequence-training speech model, a second batch of training frames that represent speech features of second training utterances; obtaining one or more second neural network parameters; and determining, by the second sequence-training speech model, one or more optimized second neural network parameters based on (i) the second batch of training frames and (ii) the one or more second neural network parameters.

公开(公告)号：US11227582B2

公开(公告)日：2022-01-18

申请号：US17143140

申请日：2021-01-06

Applicant: Google LLC

Inventor： Georg Heigold ,  Erik Mcdermott ,  Vincent O. Vanhoucke ,  Andrew W. Senior ,  Michiel A. U. Bacchiani

IPC: G10L15/06 ,  G10L15/16 ,  G10L15/183 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, by a first sequence-training speech model, a first batch of training frames that represent speech features of first training utterances; obtaining, by the first sequence-training speech model, one or more first neural network parameters; determining, by the first sequence-training speech model, one or more optimized first neural network parameters based on (i) the first batch of training frames and (ii) the one or more first neural network parameters; obtaining, by a second sequence-training speech model, a second batch of training frames that represent speech features of second training utterances; obtaining one or more second neural network parameters; and determining, by the second sequence-training speech model, one or more optimized second neural network parameters based on (i) the second batch of training frames and (ii) the one or more second neural network parameters.

公开(公告)号：US20200311491A1

公开(公告)日：2020-10-01

申请号：US16846924

申请日：2020-04-13

Applicant: Google LLC

Inventor： Christian Szegedy ,  Vincent O. Vanhoucke

IPC: G06K9/66 ,  G06N3/063 ,  G06N3/04 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for image processing using deep neural networks. One of the methods includes receiving data characterizing an input image; processing the data characterizing the input image using a deep neural network to generate an alternative representation of the input image, wherein the deep neural network comprises a plurality of subnetworks, wherein the subnetworks are arranged in a sequence from lowest to highest, and wherein processing the data characterizing the input image using the deep neural network comprises processing the data through each of the subnetworks in the sequence; and processing the alternative representation of the input image through an output layer to generate an output from the input image.

公开(公告)号：US11854534B1

公开(公告)日：2023-12-26

申请号：US18069035

申请日：2022-12-20

Applicant: Google LLC

Inventor： Georg Heigold ,  Erik Mcdermott ,  Vincent O. Vanhoucke ,  Andrew W. Senior ,  Michiel A. U. Bacchiani

IPC: G10L15/06 ,  G10L15/183 ,  G06N3/045

CPC classification number: G10L15/063 ,  G06N3/045 ,  G10L15/06 ,  G10L15/183

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, by a first sequence-training speech model, a first batch of training frames that represent speech features of first training utterances; obtaining, by the first sequence-training speech model, one or more first neural network parameters; determining, by the first sequence-training speech model, one or more optimized first neural network parameters based on (i) the first batch of training frames and (ii) the one or more first neural network parameters; obtaining, by a second sequence-training speech model, a second batch of training frames that represent speech features of second training utterances; obtaining one or more second neural network parameters; and determining, by the second sequence-training speech model, one or more optimized second neural network parameters based on (i) the second batch of training frames and (ii) the one or more second neural network parameters.

公开(公告)号：US11809955B2

公开(公告)日：2023-11-07

申请号：US17936299

申请日：2022-09-28

Applicant: Google LLC

Inventor： Christian Szegedy ,  Vincent O. Vanhoucke

IPC: G06K9/46 ,  G06N3/084 ,  G06N3/063 ,  G06N3/045 ,  G06V30/194

CPC classification number: G06N3/084 ,  G06N3/045 ,  G06N3/063 ,  G06V30/194

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for image processing using deep neural networks. One of the methods includes receiving data characterizing an input image; processing the data characterizing the input image using a deep neural network to generate an alternative representation of the input image, wherein the deep neural network comprises a plurality of subnetworks, wherein the subnetworks are arranged in a sequence from lowest to highest, and wherein processing the data characterizing the input image using the deep neural network comprises processing the data through each of the subnetworks in the sequence; and processing the alternative representation of the input image through an output layer to generate an output from the input image.

公开(公告)号：US20230014634A1

公开(公告)日：2023-01-19

申请号：US17936299

申请日：2022-09-28

Applicant: Google LLC

Inventor： Christian Szegedy ,  Vincent O. Vanhoucke

IPC: G06V30/194 ,  G06N3/063 ,  G06N3/04 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for image processing using deep neural networks. One of the methods includes receiving data characterizing an input image; processing the data characterizing the input image using a deep neural network to generate an alternative representation of the input image, wherein the deep neural network comprises a plurality of subnetworks, wherein the subnetworks are arranged in a sequence from lowest to highest, and wherein processing the data characterizing the input image using the deep neural network comprises processing the data through each of the subnetworks in the sequence; and processing the alternative representation of the input image through an output layer to generate an output from the input image.

公开(公告)号：US10977529B2

公开(公告)日：2021-04-13

申请号：US16846924

申请日：2020-04-13

Applicant: Google LLC

Inventor： Christian Szegedy ,  Vincent O. Vanhoucke

IPC: G06K9/46 ,  G06K9/66 ,  G06N3/063 ,  G06N3/04 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for image processing using deep neural networks. One of the methods includes receiving data characterizing an input image; processing the data characterizing the input image using a deep neural network to generate an alternative representation of the input image, wherein the deep neural network comprises a plurality of subnetworks, wherein the subnetworks are arranged in a sequence from lowest to highest, and wherein processing the data characterizing the input image using the deep neural network comprises processing the data through each of the subnetworks in the sequence; and processing the alternative representation of the input image through an output layer to generate an output from the input image.

公开(公告)号：US20200258500A1

公开(公告)日：2020-08-13

申请号：US16863432

申请日：2020-04-30

Applicant: Google LLC

Inventor： Georg Heigold ,  Erik McDermott ,  Vincent O. Vanhoucke ,  Andrew W. Senior ,  Michiel A.U. Bacchiani

IPC: G10L15/06 ,  G10L15/16 ,  G10L15/183 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, by a first sequence-training speech model, a first batch of training frames that represent speech features of first training utterances; obtaining, by the first sequence-training speech model, one or more first neural network parameters; determining, by the first sequence-training speech model, one or more optimized first neural network parameters based on (i) the first batch of training frames and (ii) the one or more first neural network parameters; obtaining, by a second sequence-training speech model, a second batch of training frames that represent speech features of second training utterances; obtaining one or more second neural network parameters; and determining, by the second sequence-training speech model, one or more optimized second neural network parameters based on (i) the second batch of training frames and (ii) the one or more second neural network parameters.