Patents by Inventor Xiaozhe Ren

Xiaozhe Ren 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: 20240152770
    Abstract: This application relates to the artificial intelligence field, and discloses a neural network search method and a related apparatus. The neural network search method includes: constructing attention heads in transformer layers by sampling a plurality of candidate operators during model search, to construct a plurality of candidate neural networks, and comparing performance of the plurality of candidate neural networks to select a target neural network with higher performance. In this application, a transformer model is constructed with reference to model search, so that a new attention structure with better performance than an original self-attention mechanism can be generated, and effect in a wide range of downstream tasks is significantly improved.
    Type: Application
    Filed: January 12, 2024
    Publication date: May 9, 2024
    Inventors: Hang XU, Xiaozhe REN, Yichun YIN, Li QIAN, Zhenguo LI, Xin JIANG, Jiahui GAO
  • Publication number: 20230274144
    Abstract: This application relates to the field of artificial intelligence, and provides a model training method. The method includes: obtaining a to-be-trained first neural network model, where the first neural network model includes a first operator, and the first operator is used to perform a product operation on input data and a target weight matrix; replacing the first operator in the first neural network model with a second operator, to obtain a second neural network model, where the second operator is used to perform a product operation on input data and a plurality of sub-weight matrices, and the plurality of sub-weight matrices are obtained by performing matrix factorization on the target weight matrix; and performing model training on the second neural network model to obtain a target neural network model.
    Type: Application
    Filed: March 29, 2023
    Publication date: August 31, 2023
    Inventors: Xiaozhe REN, Yichun YIN, Xin JIANG
  • Patent number: 10634618
    Abstract: The invention provides an apparatus for inspecting a light transmissible optical component. The apparatus comprises an image capturing module arranged on a first side of a support configured to hold a light transmissible optical component whilst it is being inspected. The apparatus includes an illumination device configured to shape light from a light source and to illuminate a selected portion of a surface of said light transmissible optical component with said shaped light to enable the image capturing module to capture any of a bright field image, a dark field image, or a combined bright field and dark field image of the light transmissible optical component being held by the support.
    Type: Grant
    Filed: January 23, 2018
    Date of Patent: April 28, 2020
    Assignee: Hong Kong Applied Science and Technology Research Institute Company Limited
    Inventors: Vladislav Nikitin, Wang Fei Ng, Ka Kit Wong, Xiaozhe Ren, Ying Liu
  • Publication number: 20190226997
    Abstract: The invention provides an apparatus for inspecting a light transmissible optical component. The apparatus comprises an image capturing module arranged on a first side of a support configured to hold a light transmissible optical component whilst it is being inspected. The apparatus includes an illumination device configured to shape light from a light source and to illuminate a selected portion of a surface of said light transmissible optical component with said shaped light to enable the image capturing module to capture any of a bright field image, a dark field image, or a combined bright field and dark field image of the light transmissible optical component being held by the support.
    Type: Application
    Filed: January 23, 2018
    Publication date: July 25, 2019
    Inventors: Vladislav Nitikin, Wang Fei Ng, Ka Kit Wong, Xiaozhe Ren, Ying Liu