Patents by Inventor Vincent O. Vanhoucke
Vincent O. Vanhoucke has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 10650289Abstract: 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.Type: GrantFiled: January 11, 2018Date of Patent: May 12, 2020Assignee: Google LLCInventors: Christian Szegedy, Vincent O. Vanhoucke
-
Publication number: 20200118549Abstract: 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.Type: ApplicationFiled: September 17, 2019Publication date: April 16, 2020Inventors: Georg Heigold, Erik McDermott, Vincent O. Vanhoucke, Andrew W. Senior, Michiel A.U. Bacchiani
-
Publication number: 20190377985Abstract: A neural network system that includes: multiple subnetworks that includes: a first subnetwork including multiple first modules, each first module including: a pass-through convolutional layer configured to process the subnetwork input for the first subnetwork to generate a pass-through output; an average pooling stack of neural network layers that collectively processes the subnetwork input for the first subnetwork to generate an average pooling output; a first stack of convolutional neural network layers configured to collectively process the subnetwork input for the first subnetwork to generate a first stack output; a second stack of convolutional neural network layers that are configured to collectively process the subnetwork input for the first subnetwork to generate a second stack output; and a concatenation layer configured to concatenate the pass-through output, the average pooling output, the first stack output, and the second stack output to generate a first module output for the first module.Type: ApplicationFiled: August 26, 2019Publication date: December 12, 2019Inventors: Vincent O. Vanhoucke, Christian Szegedy, Sergey Ioffe
-
Patent number: 10482873Abstract: 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.Type: GrantFiled: March 2, 2018Date of Patent: November 19, 2019Assignee: Google LLCInventors: Georg Heigold, Erik McDermott, Vincent O. Vanhoucke, Andrew W. Senior, Michiel A. U. Bacchiani
-
Patent number: 10460211Abstract: A neural network system that includes: multiple subnetworks that includes: a first subnetwork including multiple first modules, each first module including: a pass-through convolutional layer configured to process the subnetwork input for the first subnetwork to generate a pass-through output; an average pooling stack of neural network layers that collectively processes the subnetwork input for the first subnetwork to generate an average pooling output; a first stack of convolutional neural network layers configured to collectively process the subnetwork input for the first subnetwork to generate a first stack output; a second stack of convolutional neural network layers that are configured to collectively process the subnetwork input for the first subnetwork to generate a second stack output; and a concatenation layer configured to concatenate the pass-through output, the average pooling output, the first stack output, and the second stack output to generate a first module output for the first module.Type: GrantFiled: December 30, 2016Date of Patent: October 29, 2019Assignee: Google LLCInventors: Vincent O. Vanhoucke, Christian Szegedy, Sergey Ioffe
-
Patent number: 10387531Abstract: 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.Type: GrantFiled: August 18, 2015Date of Patent: August 20, 2019Assignee: Google LLCInventor: Vincent O. Vanhoucke
-
Publication number: 20180261204Abstract: 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.Type: ApplicationFiled: March 2, 2018Publication date: September 13, 2018Inventors: Georg Heigold, Erik McDermott, Vincent O. Vanhoucke, Andrew W. Senior, Michiel A.U. Bacchiani
-
Patent number: 10073817Abstract: The present disclosure relates to optimized matrix multiplication using vector multiplication of interleaved matrix values. Two matrices to be multiplied are organized into specially ordered vectors, which are multiplied together to produce a portion of a product matrix.Type: GrantFiled: October 24, 2017Date of Patent: September 11, 2018Assignee: Google LLCInventors: Nishant Patil, Matthew Sarett, Rama Krishna Govindaraju, Benoit Steiner, Vincent O. Vanhoucke
-
Patent number: 10019985Abstract: 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.Type: GrantFiled: April 22, 2014Date of Patent: July 10, 2018Assignee: Google LLCInventors: Georg Heigold, Erik McDermott, Vincent O. Vanhoucke, Andrew W. Senior, Michiel A. U. Bacchiani
-
Publication number: 20180137396Abstract: 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.Type: ApplicationFiled: January 11, 2018Publication date: May 17, 2018Inventors: Christian Szegedy, Vincent O. Vanhoucke
-
Publication number: 20180068207Abstract: 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.Type: ApplicationFiled: November 10, 2017Publication date: March 8, 2018Inventors: Christian Szegedy, Vincent O. Vanhoucke
-
Patent number: 9911069Abstract: 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.Type: GrantFiled: November 10, 2017Date of Patent: March 6, 2018Assignee: Google LLCInventors: Christian Szegedy, Vincent O. Vanhoucke
-
Patent number: 9904875Abstract: 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.Type: GrantFiled: July 14, 2017Date of Patent: February 27, 2018Assignee: Google LLCInventors: Christian Szegedy, Vincent O. Vanhoucke
-
Patent number: 9830303Abstract: The present disclosure relates to optimized matrix multiplication using vector multiplication of interleaved matrix values. Two matrices to be multiplied are organized into specially ordered vectors, which are multiplied together to produce a portion of a product matrix.Type: GrantFiled: May 5, 2017Date of Patent: November 28, 2017Assignee: Google Inc.Inventors: Nishant Patil, Matthew Sarett, Rama Krishna Govindaraju, Benoit Steiner, Vincent O. Vanhoucke
-
Publication number: 20170316286Abstract: 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.Type: ApplicationFiled: July 14, 2017Publication date: November 2, 2017Inventors: Christian Szegedy, Vincent O. Vanhoucke
-
Publication number: 20170243085Abstract: A neural network system that includes: multiple subnetworks that includes: a first subnetwork including multiple first modules, each first module including: a pass-through convolutional layer configured to process the subnetwork input for the first subnetwork to generate a pass-through output; an average pooling stack of neural network layers that collectively processes the subnetwork input for the first subnetwork to generate an average pooling output; a first stack of convolutional neural network layers configured to collectively process the subnetwork input for the first subnetwork to generate a first stack output; a second stack of convolutional neural network layers that are configured to collectively process the subnetwork input for the first subnetwork to generate a second stack output; and a concatenation layer configured to concatenate the pass-through output, the average pooling output, the first stack output, and the second stack output to generate a first module output for the first module.Type: ApplicationFiled: December 30, 2016Publication date: August 24, 2017Inventors: Vincent O. Vanhoucke, Christian Szegedy, Sergey Ioffe
-
Patent number: 9715642Abstract: 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.Type: GrantFiled: August 28, 2015Date of Patent: July 25, 2017Assignee: Google Inc.Inventors: Christian Szegedy, Vincent O. Vanhoucke
-
Patent number: 9690979Abstract: Embodiments described herein facilitate or enhance the implementation of image recognition processes which can perform recognition on images to identify objects and/or faces by class or by people.Type: GrantFiled: January 13, 2014Date of Patent: June 27, 2017Assignee: Google Inc.Inventors: Salih Burak Gokturk, Dragomir Anguelov, Lorenzo Torresani, Vincent O. Vanhoucke, Munjal Shah, Diem Thanh Vu, Kuang-chih Lee
-
Patent number: 9645974Abstract: The present disclosure relates to optimized matrix multiplication using vector multiplication of interleaved matrix values. Two matrices to be multiplied are organized into specially ordered vectors, which are multiplied together to produce a portion of a product matrix.Type: GrantFiled: March 11, 2015Date of Patent: May 9, 2017Assignee: Google Inc.Inventors: Nishant Patil, Matthew Sarett, Rama Krishna Govindaraju, Benoit Steiner, Vincent O. Vanhoucke
-
Patent number: 9542419Abstract: A similarity search may be performed on the image of a person, using visual characteristics and information that is known about the person. The search identifies images of other persons that are similar in appearance to the person in the image.Type: GrantFiled: March 20, 2015Date of Patent: January 10, 2017Assignee: Google Inc.Inventors: Vincent O. Vanhoucke, Salih Burak Gokturk, Dragomir Anguelov, Kuang-chih Lee, Munjal Shah, Ashwin Tengli