Patents by Inventor Hanzhang HU

Hanzhang HU 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).

  • AUTOMATED GENERATION OF MACHINE LEARNING MODELS
    Publication number: 20230115700
    Abstract: This document relates to automated generation of machine learning models, such as neural networks. One example system includes a hardware processing unit and a storage resource. The storage resource can store computer-readable instructions cause the hardware processing unit to perform an iterative model-growing process that involves modifying parent models to obtain child models. The iterative model-growing process can also include selecting candidate layers to include in the child models based at least on weights learned in an initialization process of the candidate layers. The system can also output a final model selected from the child models.
    Type: Application
    Filed: December 13, 2022
    Publication date: April 13, 2023
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Debadeepta DEY, Hanzhang HU, Richard A. CARUANA, John C. LANGFORD, Eric J. HORVITZ
  • Automated generation of machine learning models
    Patent number: 11556778
    Abstract: This document relates to automated generation of machine learning models, such as neural networks. One example system includes a hardware processing unit and a storage resource. The storage resource can store computer-readable instructions cause the hardware processing unit to perform an iterative model-growing process that involves modifying parent models to obtain child models. The iterative model-growing process can also include selecting candidate layers to include in the child models based at least on weights learned in an initialization process of the candidate layers. The system can also output a final model selected from the child models.
    Type: Grant
    Filed: December 7, 2018
    Date of Patent: January 17, 2023
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Debadeepta Dey, Hanzhang Hu, Richard A. Caruana, John C. Langford, Eric J. Horvitz
  • AUTOMATED GENERATION OF MACHINE LEARNING MODELS
    Publication number: 20200184327
    Abstract: This document relates to automated generation of machine learning models, such as neural networks. One example system includes a hardware processing unit and a storage resource. The storage resource can store computer-readable instructions cause the hardware processing unit to perform an iterative model-growing process that involves modifying parent models to obtain child models. The iterative model-growing process can also include selecting candidate layers to include in the child models based at least on weights learned in an initialization process of the candidate layers. The system can also output a final model selected from the child models.
    Type: Application
    Filed: December 7, 2018
    Publication date: June 11, 2020
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Debadeepta DEY, Hanzhang HU, Richard A. CARUANA, John C. LANGFORD, Eric J. HORVITZ