Patents by Inventor Brian Vosburgh

Brian Vosburgh 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).

  • Forming an artificial neural network by generating and forming of tunnels
    Patent number: 11615309
    Abstract: In an artificial neural network, integrality refers to the degree to which a neuron generates, for a given set of inputs, outputs that are near the border of the output range of a neuron. From each neural network of a pool of trained neural networks, a group of neurons with a higher integrality is selected to form a neural network tunnel (“tunnel”). The tunnel must include all input neurons and output neurons from the neural network, and some of the hidden neurons. Tunnels generated from each neural network in a pool are merged to form another neural network. The new network may then be trained.
    Type: Grant
    Filed: February 27, 2019
    Date of Patent: March 28, 2023
    Assignee: Oracle International Corporation
    Inventors: Dmitry Golovashkin, Uladzislau Sharanhovich, Brian Vosburgh, Denis B. Mukhin
  • FORMING AN ARTIFICIAL NEURAL NETWORK BY GENERATING AND FORMING OF TUNNELS
    Publication number: 20200272904
    Abstract: In an artificial neural network, integrality refers to the degree to which a neuron generates, for a given set of inputs, outputs that are near the border of the output range of a neuron. From each neural network of a pool of trained neural networks, a group of neurons with a higher integrality is selected to form a neural network tunnel (“tunnel”). The tunnel must include all input neurons and output neurons from the neural network, and some of the hidden neurons. Tunnels generated from each neural network in a pool are merged to form another neural network. The new network may then be trained.
    Type: Application
    Filed: February 27, 2019
    Publication date: August 27, 2020
    Inventors: DMITRY GOLOVASHKIN, ULADZISLAU SHARANHOVICH, BRIAN VOSBURGH, DENIS B. MUKHIN
  • Method and system for mapping between markup language document and an object model
    Patent number: 7089533
    Abstract: Mapping operations between a markup language document and an object model are executed in response to a request from a client application. The mapping operations include a read, write, update, or delete operation. To map the markup language document to the object model, mapping meta-data is used, which contains information as to how the markup language element maps to an attribute and/or a relationship of the object model.
    Type: Grant
    Filed: August 1, 2001
    Date of Patent: August 8, 2006
    Assignee: OIC Acquisition I Corp
    Inventor: Brian Vosburgh
  • Method and system for mapping between markup language document and an object model
    Publication number: 20040205552
    Abstract: Mapping operations between a markup language document and an object model are executed in response to a request from a client application. The mapping operations include a read, write, update ordelete operation. To map the markup language document to the object model, mapping meta-data is used, which contains information as to how the markup language element maps to an attribute and/or a relationship of the object model.
    Type: Application
    Filed: August 1, 2001
    Publication date: October 14, 2004
    Inventor: Brian Vosburgh