Patents by Inventor Minhao Cheng

Minhao Cheng 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: 20240232631
    Abstract: Methods, systems, apparatus, and tangible non-transitory carrier media encoded with one or more computer programs for classifying an input text block into a sequence of one or more classes in a multi-level hierarchical classification taxonomy. In accordance with particular embodiments, a source sequence of inputs corresponding to the input text block is processed, one at a time per time step, with an encoder recurrent neural network (RNN) to generate a respective encoder hidden state for each input, and the respective encoder hidden states are processed, one at a time per time step, with a decoder RNN to produce a sequence of outputs representing a directed classification path in a multi-level hierarchical classification taxonomy for the input text block.
    Type: Application
    Filed: May 19, 2023
    Publication date: July 11, 2024
    Inventors: Minhao Cheng, Xiaocheng Tang, Chu-Cheng Hsieh
  • Publication number: 20240135183
    Abstract: Methods, systems, apparatus, and tangible non-transitory carrier media encoded with one or more computer programs for classifying an input text block into a sequence of one or more classes in a multi-level hierarchical classification taxonomy. In accordance with particular embodiments, a source sequence of inputs corresponding to the input text block is processed, one at a time per time step, with an encoder recurrent neural network (RNN) to generate a respective encoder hidden state for each input, and the respective encoder hidden states are processed, one at a time per time step, with a decoder RNN to produce a sequence of outputs representing a directed classification path in a multi-level hierarchical classification taxonomy for the input text block.
    Type: Application
    Filed: May 18, 2023
    Publication date: April 25, 2024
    Inventors: Minhao Cheng, Xiaocheng Tang, Chu-Cheng Hsieh
  • Patent number: 11416775
    Abstract: Techniques for training robust machine learning models for adversarial input data. Training data for a machine learning (ML) model is received. The training data includes a plurality of labels for data elements. First modified training data is generated by modifying one or more of the plurality of labels in the training data using parameterized label smoothing with a first optimization parameter. The ML model is trained using the first modified training data.
    Type: Grant
    Filed: April 17, 2020
    Date of Patent: August 16, 2022
    Assignee: International Business Machines Corporation
    Inventors: Pin-yu Chen, Sijia Liu, Shiyu Chang, Payel Das, Minhao Cheng
  • Publication number: 20210326745
    Abstract: Techniques for training robust machine learning models for adversarial input data. Training data for a machine learning (ML) model is received. The training data includes a plurality of labels for data elements. First modified training data is generated by modifying one or more of the plurality of labels in the training data using parameterized label smoothing with a first optimization parameter. The ML model is trained using the first modified training data.
    Type: Application
    Filed: April 17, 2020
    Publication date: October 21, 2021
    Inventors: Pin-yu CHEN, Sijia LIU, Shiyu CHANG, Payel DAS, Minhao CHENG
  • Publication number: 20190171913
    Abstract: Methods, systems, apparatus, and tangible non-transitory carrier media encoded with one or more computer programs for classifying an input text block into a sequence of one or more classes in a multi-level hierarchical classification taxonomy. In accordance with particular embodiments, a source sequence of inputs corresponding to the input text block is processed, one at a time per time step, with an encoder recurrent neural network (RNN) to generate a respective encoder hidden state for each input, and the respective encoder hidden states are processed, one at a time per time step, with a decoder RNN to produce a sequence of outputs representing a directed classification path in a multi-level hierarchical classification taxonomy for the input text block.
    Type: Application
    Filed: December 4, 2017
    Publication date: June 6, 2019
    Applicant: Slice Technologies, Inc.
    Inventors: Minhao Cheng, Xiaocheng Tang, Chu-Cheng Hsieh