Patents by Inventor Richard BLAND

Richard BLAND 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: 20240119315
    Abstract: A layered machine learning system for processing data. The machine learning system comprises decision trees with different depths. An iterative training process is performed on the layered machine learning system to determine the structures of the decision trees based on prior predictions. The fitted decision trees are further configured to update leaf values with a gradient boosting method. By cumulating the predictions of decisions trees in prior iterations, interaction effects are modeled among different depths within the layered machine learning system.
    Type: Application
    Filed: December 6, 2023
    Publication date: April 11, 2024
    Inventors: Rachael MCNAUGHTON, Richard BLAND, Colin TOWERS, William JAMES
  • Publication number: 20230419128
    Abstract: A layered machine learning system for processing data. The machine learning system comprises decision trees with different depths. An iterative training process is performed on the layered machine learning system to determine the structures of the decision trees based on prior predictions. The fitted decision trees are further configured to update leaf values with a gradient boosting method. By cumulating the predictions of decisions trees in prior iterations, interaction effects are modeled among different depths within the layered machine learning system.
    Type: Application
    Filed: April 17, 2023
    Publication date: December 28, 2023
    Inventors: Rachael MCNAUGHTON, Richard BLAND, Colin TOWERS, William JAMES
  • Patent number: 11853906
    Abstract: A layered machine learning system for processing data. The machine learning system comprises decision trees with different depths. An iterative training process is performed on the layered machine learning system to determine the structures of the decision trees based on prior predictions. The fitted decision trees are further configured to update leaf values with a gradient boosting method. By cumulating the predictions of decisions trees in prior iterations, interaction effects are modeled among different depths within the layered machine learning system.
    Type: Grant
    Filed: April 17, 2023
    Date of Patent: December 26, 2023
    Assignee: Towers Watson Software Limited
    Inventors: Rachael McNaughton, Richard Bland, Colin Towers, William James
  • Publication number: 20210101351
    Abstract: Apparatuses, devices, systems 1 and methods for resin transfer moulding of composite articles are disclosed. A mould enclosure enclosing a fibre pack (9) is provided and one or more resin ports (6a-6e) are provided along a resin flow path within the fibre pack (9). Resin ingress into the fibre pack (9) is controlled via valves (44a-44e) or a flow control mechanism (30), each being operable to impose a flow rate on resin passing into the fibre pack (9).
    Type: Application
    Filed: December 18, 2018
    Publication date: April 8, 2021
    Inventors: Richard BLAND, William HARRIS, Simon VINCENT, Oliver POWLESLAND