Patents by Inventor Hoang Trieu Trinh

Hoang Trieu Trinh 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).

  • Learning longer-term dependencies in neural network using auxiliary losses
    Patent number: 11501168
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for structuring and training a recurrent neural network. This describes a technique that improves the ability to capture long term dependencies in recurrent neural networks by adding an unsupervised auxiliary loss at one or more anchor points to the original objective. This auxiliary loss forces the network to either reconstruct previous events or predict next events in a sequence, making truncated backpropagation feasible for long sequences and also improving full backpropagation through time.
    Type: Grant
    Filed: February 11, 2019
    Date of Patent: November 15, 2022
    Assignee: Google LLC
    Inventors: Andrew M. Dai, Quoc V. Le, Hoang Trieu Trinh, Thang Minh Luong
  • LEARNING LONGER-TERM DEPENDENCIES IN NEURAL NETWORK USING AUXILIARY LOSSES
    Publication number: 20190251449
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for structuring and training a recurrent neural network. This describes a technique that improves the ability to capture long term dependencies in recurrent neural networks by adding an unsupervised auxiliary loss at one or more anchor points to the original objective. This auxiliary loss forces the network to either reconstruct previous events or predict next events in a sequence, making truncated backpropagation feasible for long sequences and also improving full backpropagation through time.
    Type: Application
    Filed: February 11, 2019
    Publication date: August 15, 2019
    Inventors: Andrew M. Dai, Quoc V. Le, Hoang Trieu Trinh, Thang Minh Luong