Patents by Inventor Angus LAMB

Angus LAMB 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).

  • AUXILIARY MODEL FOR PREDICTING NEW MODEL PARAMETERS
    Publication number: 20250036947
    Abstract: A computer-implemented method of training an auxiliary machine learning model to predict a set of new parameters of a primary machine learning model, wherein the primary model is configured to transform from an observed subset of a set of real-world features to a predicted version of the set of real-world features.
    Type: Application
    Filed: September 3, 2024
    Publication date: January 30, 2025
    Inventors: Cheng ZHANG, Angus LAMB, Evgeny Sergeevich SAVELIEV, Yingzhen LI, Camilla LONGDEN, Pashmina CAMERON, Sebastian TSCHIATSCHEK, Jose Miguel Hernández LOBATO, Richard TURNER
  • Auxiliary model for predicting new model parameters
    Patent number: 12165056
    Abstract: A computer-implemented method of training an auxiliary machine learning model to predict a set of new parameters of a primary machine learning model, wherein the primary model is configured to transform from an observed subset of a set of real-world features to a predicted version of the set of real-world features.
    Type: Grant
    Filed: November 11, 2020
    Date of Patent: December 10, 2024
    Assignee: Microsoft Technology Licensing, LLC.
    Inventors: Cheng Zhang, Angus Lamb, Evgeny Sergeevich Saveliev, Yingzhen Li, Camilla Longden, Pashmina Cameron, Sebastian Tschiatschek, Jose Miguel Hernández Lobato, Richard Turner
  • AUXILIARY MODEL FOR PREDICTING NEW MODEL PARAMETERS
    Publication number: 20220147818
    Abstract: A computer-implemented method of training an auxiliary machine learning model to predict a set of new parameters of a primary machine learning model, wherein the primary model is configured to transform from an observed subset of a set of real-world features to a predicted version of the set of real-world features.
    Type: Application
    Filed: November 11, 2020
    Publication date: May 12, 2022
    Inventors: Cheng ZHANG, Angus LAMB, Evgeny Sergeevich SAVELIEV, Yingzhen LI, Camilla LONGDEN, Pashmina CAMERON, Sebastian TSCHIATSCHEK, Jose Miguel Hernández LOBATO, Richard TURNER