Patents by Inventor Hieu Hy Pham

Hieu Hy Pham 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).

  • Publication number: 20240062062
    Abstract: A method for determining a placement for machine learning model operations across multiple hardware devices is described.
    Type: Application
    Filed: October 3, 2023
    Publication date: February 22, 2024
    Inventors: Samuel Bengio, Mohammad Norouzi, Benoit Steiner, Jeffrey Adgate Dean, Hieu Hy Pham, Azalia Mirhoseini, Quoc V. Le, Naveen Kumar, Yuefeng Zhou, Rasmus Munk Larsen
  • Patent number: 11803747
    Abstract: A method for determining a placement for machine learning model operations across multiple hardware devices is described.
    Type: Grant
    Filed: May 20, 2020
    Date of Patent: October 31, 2023
    Assignee: Google LLC
    Inventors: Samuel Bengio, Mohammad Norouzi, Benoit Steiner, Jeffrey Adgate Dean, Hieu Hy Pham, Azalia Mirhoseini, Quoc V. Le, Naveen Kumar, Yuefeng Zhou, Rasmus Munk Larsen
  • Publication number: 20230154161
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using memory-optimized contrastive learning to train image encoder and text encoder neural networks.
    Type: Application
    Filed: November 16, 2022
    Publication date: May 18, 2023
    Inventors: Hieu Hy Pham, Zihang Dai, Golnaz Ghiasi, Hanxiao Liu, Wei Yu, Mingxing Tan, Quoc V. Le
  • Patent number: 11455514
    Abstract: A method for determining a placement for machine learning model operations across multiple hardware devices includes receiving data specifying machine learning operations, and determining a placement that assigns each of the operations specified by the data to a respective device from the multiple hardware devices.
    Type: Grant
    Filed: August 28, 2019
    Date of Patent: September 27, 2022
    Assignee: Google LLC
    Inventors: Benoit Steiner, Anna Darling Goldie, Jeffrey Adgate Dean, Hieu Hy Pham, Azalia Mirhoseini, Quoc V. Le
  • Publication number: 20220188636
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network using meta pseudo-labels. One of the methods includes training a student neural network using pseudo-labels generated by a teacher neural network that is being trained jointly with the student neural network.
    Type: Application
    Filed: December 14, 2021
    Publication date: June 16, 2022
    Inventors: Hieu Hy Pham, Zihang Dai, Qizhe Xie, Quoc V. Le
  • Publication number: 20210232929
    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, a batch of output sequences, each output sequence in the batch specifying a respective subset of a plurality of components of a large neural network that should be active during the processing of inputs by the large neural network; for each output sequence in the batch: determining a performance metric of the large neural network on the particular neural network task (i) in accordance with current values of the large network parameters and (ii) with only the subset of components specified by the output sequences active; and using the performance metrics for the output sequences in the batch to adjust the current values of the controller parameters of the controller neural network.
    Type: Application
    Filed: April 16, 2021
    Publication date: July 29, 2021
    Inventors: Barret Zoph, Yun Jia Guan, Hieu Hy Pham, Quoc V. Le
  • Patent number: 10984319
    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, a batch of output sequences, each output sequence in the batch specifying a respective subset of a plurality of components of a large neural network that should be active during the processing of inputs by the large neural network; for each output sequence in the batch: determining a performance metric of the large neural network on the particular neural network task (i) in accordance with current values of the large network parameters and (ii) with only the subset of components specified by the output sequences active; and using the performance metrics for the output sequences in the batch to adjust the current values of the controller parameters of the controller neural network.
    Type: Grant
    Filed: April 27, 2020
    Date of Patent: April 20, 2021
    Assignee: Google LLC
    Inventors: Barret Zoph, Yun Jia Guan, Hieu Hy Pham, Quoc V. Le
  • Publication number: 20200279163
    Abstract: A method for determining a placement for machine learning model operations across multiple hardware devices is described.
    Type: Application
    Filed: May 20, 2020
    Publication date: September 3, 2020
    Inventors: Samuel Bengio, Mohammad Norouzi, Benoit Steiner, Jeffrey Adgate Dean, Hieu Hy Pham, Azalia Mirhoseini, Quoc V. Le, Naveen Kumar, Yuefeng Zhou, Rasmus Munk Larsen
  • Publication number: 20200265315
    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, a batch of output sequences, each output sequence in the batch specifying a respective subset of a plurality of components of a large neural network that should be active during the processing of inputs by the large neural network; for each output sequence in the batch: determining a performance metric of the large neural network on the particular neural network task (i) in accordance with current values of the large network parameters and (ii) with only the subset of components specified by the output sequences active; and using the performance metrics for the output sequences in the batch to adjust the current values of the controller parameters of the controller neural network.
    Type: Application
    Filed: April 27, 2020
    Publication date: August 20, 2020
    Inventors: Barret Zoph, Yun Jia Guan, Hieu Hy Pham, Quoc V. Le
  • Patent number: 10692003
    Abstract: A method for determining a placement for machine learning model operations across multiple hardware devices is described.
    Type: Grant
    Filed: June 19, 2019
    Date of Patent: June 23, 2020
    Assignee: Google LLC
    Inventors: Samuel Bengio, Mohammad Norouzi, Benoit Steiner, Jeffrey Adgate Dean, Hieu Hy Pham, Azalia Mirhoseini, Quoc V. Le, Naveen Kumar, Yuefeng Zhou, Rasmus Munk Larsen
  • Publication number: 20190392294
    Abstract: A method for determining a placement for machine learning model operations across multiple hardware devices includes receiving data specifying machine learning operations, and determining a placement that assigns each of the operations specified by the data to a respective device from the multiple hardware devices.
    Type: Application
    Filed: August 28, 2019
    Publication date: December 26, 2019
    Inventors: Benoit Steiner, Anna Darling Goldie, Jeffrey Adgate Dean, Hieu Hy Pham, Azalia Mirhoseini, Quoc V. Le
  • Patent number: 10438113
    Abstract: A method for determining a placement for machine learning model operations across multiple hardware devices includes receiving data specifying machine learning operations, and determining a placement that assigns each of the operations specified by the data to a respective device from the multiple hardware devices.
    Type: Grant
    Filed: July 19, 2018
    Date of Patent: October 8, 2019
    Assignee: Google LLC
    Inventors: Benoit Steiner, Anna Darling Goldie, Jeffrey Adgate Dean, Hieu Hy Pham, Azalia Mirhoseini, Quoc V. Le
  • Publication number: 20190303761
    Abstract: A method for determining a placement for machine learning model operations across multiple hardware devices is described.
    Type: Application
    Filed: June 19, 2019
    Publication date: October 3, 2019
    Inventors: Samy Bengio, Mohammad Edward Norouzi, Benoit Steiner, Jeffrey Adgate Dean, Hieu Hy Pham, Azalia Mirhoseini, Quoc V. Le, Naveen Kumar, Yuefeng Zhou, Rasmus Munk Larsen
  • Publication number: 20190026624
    Abstract: A method for determining a placement for machine learning model operations across multiple hardware devices includes receiving data specifying machine learning operations, and determining a placement that assigns each of the operations specified by the data to a respective device from the multiple hardware devices.
    Type: Application
    Filed: July 19, 2018
    Publication date: January 24, 2019
    Inventors: Benoit Steiner, Anna Darling Goldie, Jeffrey Adgate Dean, Hieu Hy Pham, Azalia Mirhoseini, Quoc V. Le